Cite4Me: Semantic Retrieval and Analysis of Scientific Publications Bernardo Pereira Nunes Besnik Fetahu Marco Antonio Casanova PUC-Rio L3S Research Center PUC-Rio Rio de Janeiro, Brazil Appelstrasse 9a Rio de Janeiro, Brazil bnunes@inf.puc-rio.br Hannover, Germany casanova@inf.puc-rio.br fetahu@l3s.de ABSTRACT lications3 . However, current approaches by main digital library This paper presents the Cite4Me Web application and its features providers, such as ACM Digital Library4 and Elsevier5 , do not created for the LAK Challenge 2013. The Web application focuses represent the current state of research on exploring resources us- on two main directions: (i) interlinking of the LAK dataset with ing approaches from Information Retrieval, Information Extraction related data sources from the Linked Open Data cloud; and (ii) and Semantic Web. Thus, get an overview of research topics, find providing innovative search, visualization, retrieval and recommen- publications and discover new nomenclatures are an arduous and dation of scientific publications from the LAK dataset and related laborious task that are not always successful. interlinked resources. Our approach is based on semantic and co- In this paper, we introduce Cite4Me a novel application for ex- occurrence relations to provide new browsing experiences to Web ploratory search, retrieval and visualization of scientific publica- users and an overview of scientific data available. Furthermore, we tions. Cite4Me intends to provide to the end users a single point for present a detailed analysis of the LAK dataset along with applica- accessing papers and hence reducing efforts of searching in several tions which contributes to the development of the learning analytics data sources. Our system takes advantage of reference datasets, field. such as DBpedia6 , to explore semantic relationships between sci- entific papers and user queries. Additionally, an analysis of topic coverage and shared concepts from related educational datasets, ex- 1. INTRODUCTION tracted from the Linked Open Data cloud, will be introduced. The volume of information on the Web has been growing steadily The remaining of the paper is organized as follows. Section 2 over the last decade and has doubled every two years. The vast presents the approach used for searching, retrieving and recom- amount of data available on the Web along with new means of mending papers. Section 3 describes the process of dataset dis- communications have transformed our society, including the way covery and interlinking and Section 4 shows a brief result analysis we work, live, relate to each other and learn. of the data discovery. Finally, Section 5 presents related work and In the midst of change, the Learning Analytics emerges to make Section 6 presents some concluding remarks. sense of the produced educational data reported by learners, pro- fessors, institutions and so on. Analyzing and understanding the 2. CITE4ME changes along the past years help us to understand the current state As one of the main goals of the field of “Learning Analytics” is and be aware of the forthcoming trends, enabling a new outlook of to support students in their learning process, we developed a Web the future of learning. application called Cite4Me7 that assists students in making deci- A recent challenge initiative of SOLAR1 and LinkedUp2 project sions to find scientific publications and identify relevant research arises to leverage the creation of tools that enables the analysis, topics. visualization, browsing and recommendation of scientific and edu- Cite4Me implements semantic and co-occurrence methods to (a) cational data. search and retrieve scientific publications; and (b) recommend sci- Although the scientific field has fostered the creation of new entific publications. Moreover, it provides a Web interface that fa- applications in several areas, such as medical, biology, physics, cilitates the search for publications and may help users on discov- amongst others, the information access is based mostly on free ering related terms to a given query. text search and on hierarchical classification system of the pub- In this section, we provide an overview of the major features 1 of the Web application and its Web interface that assist users to Society for Learning Analytics Research - http://www. explore scientific data on the Web. solaresearch.org 2 http://linkedup-project.eu/ 2.1 Search and Retrieval Cite4Me relies on search functionalities to meet the users needs. Briefly, we implemented standard Information Retrieval (IR) and Semantic Web (SW) approaches to retrieve and recommend scien- tific papers to the users. We divided this subsection into (i) free text 3 http://www.acm.org/about/class/ 4 http://dl.acm.org 5 Copyright c 2013 by the papers’ authors. Copying permitted only for pri- http://www.elsevier.com 6 vate and academic purposes. http://dbpedia.org 7 LAK-Data Challenge ’13 Leuven, Belgium http://www.cite4me.com/ search; (ii) exploratory search; and (iii) semantic search. for the entities contained in a publication. Finally, the ranking of the results is based on the sum of the tf-idf scores of the matching 2.1.1 Free Text Search concepts. The purpose of the free text search functionality is to offer users Figure 2 illustrates the semantic search functionality. It also gen- the abilities to search for mentions, titles and authors of academic erates a tag cloud from matching publications, showing the most publications contained in the LAK dataset. Even though, this func- prominent terms for a given query. Specifically, the tag cloug based tionality is similar to existing digital libraries, we agree that this is a on the results helps the users to have an insight about the topics and basic functionality that must be provided by our application. There- may assist in finding related terms previously unknown by them. fore, we use standard vector space models (tf-idf ) for indexing and retrieving documents. 2.2 Paper recommendation The tf-idf scores were computed for each term extracted from the Another key feature of our system is the paper recommendation publication content after applying stemming [14]. Furthermore, the based on semantic relationships extracted from reference datasets. searching functionality offers boolean queries with standard oper- The recommendation is based on a previous work [12, 11], where ators, such as ’OR’, ’AND’, and also a ranking of the matching we exploit the number of paths and the distance (length of a path) publications based on the sum of tf-idf scores from the individual between given entities to compute a relatedness score between ex- query terms. tracted entities and associated documents. The first step to measure In summary, our free text search provides to the users publica- the relatedness between documents is to compute the semantic con- tions (P) that match query terms and non-matching publications nectivity score (S CS e ) of the entities found in each text (see Eq. 2). P0 , which are related to P according to a degree of similarity (see Eq. 1), but does not contain the query terms. τ X The similarity between a matching publication P and other non- S CS e (a, b) = βl · |paths (a,b) | (2) matching publication P0 in the LAK dataset is measured by the l=1 standard cosine similarity measure, which is built on top of the where |paths (a,b) | is the number of paths between a and b of length l computed tf-idf scores. and 0 < β ≤ 1 is a positive damping factor. As in [12, 11], we used β = 0.5 as our damping factor. Furthermore, we also constrained P · P0 the length of a path to τ = 4. S im(P, P0 ) = (1) |P||P0 | Based on the score for entities, we then define the semantic con- nectivity score (S CS w ) between two documents W1 and W2 as fol- where P and P0 represent the tf-idf scores for the terms in two dis- lows: tinct publications.     2.1.2 Exploratory Search    X |E 1 ∩ E 2 |  1 S CS w (W1 , W2 )=  S CS e (e1 , e2 ) +  ∗ (3) In this section, we provide detailed insights on the exploratory  e1 ∈E1 2  |E1 | ∗ |E2 |   search functionality of our application. As a preliminary step to e2 ∈E2 e1 ,e2 provide analytics and information about the actual content and top- ics coverage, all the scientific publications contained in the LAK where Ei is the set of entities associated with Wi , for i = 1, 2. Note dataset are previously enriched. The enrichment process was per- that documents that contain the same entities receive an extra bonus formed using DBpedia Spotlight API8 , where entities, entity types (the second term on the right-hand side of Eq. 3). and their respective categories were extracted. Thus, a list of documents pairs is generated and ranked according After the enrichment process, we cluster the publications accord- the score and suggested to the user. Figure 3 illustrates the paper ing to entities and its categories found in each document. The publi- recommendation process computed based on S CS w . cations are clustered in a tree-based structure over the enrichments. Note that, each node of the tree represents a topic in which a pub- lication under this node covers. Thus, the exploratory search is 3. DATASET DISCOVERY AND INTER- performed through the topics covered by each publication. LINKING The process of linking publications, categories and extra re- This section briefly describes the datasets used on automatic re- sources is mediated by DBpedia knowledge graph, where we use lated data discovery from DataHub9 and future steps on dataset dis- the dcterms:subject property to match the resources. covery and interlinking. Thus, as a result, the exploratory search provides a way to explore resources through the connections between their topics, 3.1 LAK Dataset which facilitates the search for topically related resources. Figure 1 The LAK dataset contains the metadata of the papers published shows the exploratory search. in the proceedings of LAK conference 2011-12, a special issue of Learning and Knowledge Analytics: Educational Technology & 2.1.3 Semantic Search Society, the proceedings of the International Conference on Educa- Cite4Me provides also a semantic search engine that assists users tional Data Mining (2008-12) and the Journal of Educational Data to find publications semantically related to the query terms. Analo- Mining (2008-12). In total, 315 descriptions of papers containing gously to explicit semantic analysis (ESA) technique [5], the relat- detailed information about authors, institutions, conference venues edness score, is computed between the enriched concepts found in and the full content of the paper were available. the publications’ content. Basically, the semantic search is an adaptation of the free text 3.2 Data Analysis search presented in the Section 2.1.1. Instead of computing the The goal of the data analysis procedure is to align the various tf-idf scores for the words in a text, it computes the tf-idf score publications in the LAK dataset based on mutual information, such 8 9 http://dbpedia.org/spotlight http://www.datahub.io Figure 1: Preview of the exploratory search funcionality. Figure 2: Preview of the semantic search funcionality. Figure 3: An example of paper recommendation based on S CS w . 4. EVALUATION OF DATA ANALYSIS AND DATA DISCOVERY This section presents an overview of the results obtained by an- alyzing the LAK dataset with respect to the constructed feature set that describes topics covered by individual publications. Moreover, based on the data analysis procedure and shared information, we show that the establishment of links between the different publica- tions within the LAK dataset and from other datasets in DataHub is possible. In the following subsections, we show the analysis of the LAK dataset and the discovery of relevant datasets and publications. 4.1 Data Analysis The data analysis of the LAK dataset focuses mostly on assess- ing the individual publications for their topic coverage. In this man- ner, we build a connected data graph consisting of the individual publications and items from the feature set. This step is necessary Figure 4: Relevant Dataset Discovery Framework based on to provide the exploratory search functionality, where based on the the generated feature set used to query DataHub Linked Data established edges between publications and feature set items, we provider. can navigate through the publications or topics of interest. There- fore, the results obtained with respect to the constructed feature set and LAK dataset graph are shown in what follows. as the topics covered by them. This is achieved using well estab- Table 1 shows the top ranked items for each of the feature sets, lished datasets like DBpedia10 and Freebase11 , where a reference along with the number of associations an item has with respect to point for the unstructured textual content of publications is created all publications (entity, category and type items). Figure 5 shows through an enrichment process. the constructed data graph for the LAK dataset. Again, the enrichment process is carried out using DBpedia Spotlight12 [10] and addresses several issues of significant impor- 4.2 Data Discovery tance. For instance, it offers several advantages such as: (i) identi- After creating the feature set based on the information provided fication of (common) named entities, (ii) disambiguation; and (iii) from reference datasets, we are able to query for relevant datasets expansion of the limited dataset and resource descriptions with ad- in DataHub. ditional background knowledge. Thus, for the top ranked feature set items, the data discovery for relevant resources is considered. Table 2 shows the discovered resources and datasets for the top-10 entity items. Note that, we fo- 3.3 Data Discovery cus only on bibliographic datasets, since we aim at recommending Our Web application uses as its starting point the instances in topically related scientific publications. Due to the lack of bib- the LAK dataset to automatically explore and recommend to users, liographic datasets, we were not able to find related publications datasets that covers similar topics. In order to query, detect and for all entities considered. Table 2 summarizes the discovered re- interlink related datasets, we chose the DataHub as a data provider. sources. The dataset names are represented by their acronyms as DataHub serves as a collecting point of datasets from various fields follows: b3kat - “Bayerische Staatsbibliothek", hebis - “Hessis- and currently it has over 5000 datasets. Note that, from the large ches Bibliotheks Informations System" and npg - “Nature Publish- number of datasets, only 300 datasets are provided as Linked Open ing Group - ALL". Data. As the latter is the main focus of our work, the analysis and Additionally, from the set of 96 bibliographic datasets available, interlinking process is focused for such datasets. only a few of them were offered as Linked Data, thus narrowing Briefly, the data discovery is performed using CKAN13 data our search space for relevant resources. management framework from DataHub, where based on data anal- ysis and user interests (such as topics covered by a publica- Entity b3kat hebis npg tion/resource) related datasets are suggested. Data 14 0 12 Additionally, we provide to the user a set of resources, amongst Learning 5 0 1 other data analytics, that enables the user to harvest and correlate Data mining 0 0 0 new information from the discovered resources, considering the Algorithm 4 0 0 LAK dataset as a starting point of such discovery. Education 17 1 2 This approach presents several advantages such as the adoption Analysis 42 1 6 and the widespread use of Linked Data principles for publishing Student 7 1 1 scientific papers. Nowadays, many conferences make their pro- Knowledge 11 0 0 ceedings and journals freely accessible, hence our approach would Methodology 4 0 1 take advantage of such open data and offer users topically relevant Statistics 7 0 1 papers for a particular resource in the LAK dataset. Table 2: Number of discovered resources from the bibliographic 10 group for the top ranked items from the entity feature set, based http://dbpedia.org 11 http://www.freebase.com/ on the LAK dataset. 12 http://spotlight.dbpedia.org/ 13 http://www.ckan.org Entity Assoc. Category Assoc. Type Assoc. Data 90 Educational_psychology 161 DBpedia:TopicalConcept 150 Learning 80 Data_analysis 150 Freebase:/book 142 Data_mining 67 Learning 139 Freebase:/book/book_subject 142 Algorithm 50 Scientific_method 137 Freebase:/media_common 138 Education 49 Neuropsychological_assessment 136 Freebase:/media_common/quotation_subject 136 Analysis 48 Greek_loanwords 135 Freebase:/computer 125 Student 46 Data 131 Freebase:/education 122 Knowledge 46 Evaluation_methods 129 Freebase:/education/field_of_study 120 Methodology 42 Computer_data 126 Freebase:/computer/software_genre 120 Statistics 41 Research_methods 124 Freebase:/internet 118 System 37 Systems_science 118 Freebase:/internet/website_category 118 Scientific_modelling 37 Formal_sciences 108 Freebase:/award 114 Prediction 36 Data_management 108 Freebase:/media_common/media_genre 105 Data_set 36 Cognitive_science 107 Freebase:/organization 103 Statistical_classification 30 Statistical_terminology 107 Freebase:/award/award_discipline 103 Evaluation 29 Developmental_psychology 101 Freebase:/business 102 Standard_deviation 29 Intelligence 93 Freebase:/organization/organization_sector 99 Probability 28 Data_mining 91 Freebase:/people 99 Behavior 26 Critical_thinking 87 Freebase:/film 94 Interaction 24 Thought 84 Freebase:/book/periodical_subject 93 Table 1: Top ranked items from the feature set for the LAK Dataset, from the dataset analysis. Industrial processes Unit operations Laboratory techniques Distillation Separation processes Paper Booksproducts http://data.linkeded... Quantification Computer Multivariable security mo... calculus Differential Religious operators fundamenta... Genetic British algorithms Analog brands Clothing circuits retailers o... Retail Genetic companies Theories Fashion programming design of of law ...algorit... Reproduction Evolutionary Companies Propositions establishe... Teachable Companiesunits for ... ininference Supermarkets based Immediate L... of Nort... 1884 Flynn's taxonomy establishments Department ... Zoology stores Department Spirituality stores of... Popular MarksElectronic & Spencer design Military Java specification lang... r...lan... Competition JVM programming Java programming Cluster computing Fault-tolerant compu... Mediaculture studies Legal terms Multiple births Electronics terms Economic Social statusproblems Local area networks Supercomputers Narcissism JavaProgramming platform language... Theology School examinations Educational qualific... Concurrent Oligarchy programmi... Social events Russell Group 1951 introductions Musical notation Predicate logic Logic symbols CaseLawyers Western Authority Reserve... Propositional calculus Marxist theory Lecturers Ecclesiastical titles institut... Educational Lists byofcountry History Oxbridge Cambridge Host Artisans cities ofBay theCompany... C... Organisations based Coimbra ... Group Hudson's Populated Orders places est... ofEdmonton magnitude University Visitor of Cambri... Classes of computers Anglican Law Culture in attractions Cambridge... ecclesiasti... degrees Counterculture Hybrid vehicles Electric vehicles Kindness Populated Garment places est... industry Anglican Universities priests and col... Drawing http://data.linkeded... Legalestablishments 1209 education ... Engines Economic development Development economics Secret Military military projects Manhattan prog... Project Machines Systems of formal lo... Syntax Atomic bombings Military of H... of ... history Environmental design Articles Military Codeofnames withhistory exampl... ... Landscape Architecturearchitecture Multilingual Philosophy Programming Inverse problems websites of biology language... Criticism Nuclear Review weapons websites prog... Crystallography Internet activism Articles Musical with of Units exampl... frequency Visual arts physical ... Individual Art of media Lexis (linguistics) Approximation algori... Collaborative Dynamically Programming Developmental projects biology Realitytyped language... pr... by type Nucleartechniques history Literary PhilosophyofRhythm t... concepts Computational physics Works art General GNUstep Customary Objective-C encyclopedias units NeXTof m... Nuclear weapons of t... Computer physics String eng... (computer sci... Discrete geometry Search Continuous Habitat Wikipedia algorithms Wikimedia projects mappings (ecology) te... Operators (programmi... HistoryMathematical Chemical Landscape ecology constants Open properties Mineralogy Free content encyclopedias projects Discovery Communicat... Video game development Condensed Articles withOnline matter exampl... Lexical dictionaries Commerce phy...databases Mass Television channels Discovery ... tel... Channel English-language Creative Online Internet Commons-lic... Functional programmingencyclopedias properties ... ForcePhysiology C programming Class-based langua... programm... Power laws Imperial Tails Statistical Grammatical ofunits probability... mechanics cases Searching Structural engineering Quantity Modes Bridges Catholic Melody music types music Ancient Greek Architectural Higher Higher education education commun... in ... in ... Personality MBTI types tests Automotive Automobile transmiss... transmiss... Personality Jungian typologies tradition Mechanical Engagementpower con... http://data.linkeded... Symbols Notation Logical connectives Semiotics Knowledge bases Military units ando... f... Academic Classical logic United Ad-hoc States Taskunits forcesandNavy for... Model theory ExpertScience witnesses Peerliterature review VirtuePsychologists Tests studies 19th-century 1856mathema... births Acronyms MentalMusical health profes... Safety AIDS origin hypotheses Pandemics Association of Indep... Master's Scientists degrees composition SaintRussian Petersburg Sta... statisticians Health Syndromes disasters Political theories HIV/AIDS Formal languages Proof theory Vocabulary 20th-century Nationalism mathema... Monetaryineconomics Set theory Trigonometry Christian Combat Measuringiconography instruments People from Ryazan Sovereignty Federalism Quality the Un... management Paper Cross symbols Christian symbols 1922 deaths Enterprise architect... Papermaking Stationery Computer storage media Heraldic ordinaries Sustainability Full Members Aftermath of war Boolean of the ... algebra InformationFoodarchitects Electronics safety Recursion Punched Unit record card equipment Christian terms MilitaryTransducers operations ... LogicalGrief calculi Intention Pragmatics IBM unit Self care record equi... Evidence law Programming language... Religious symbols Three-digit telephon... Cognitive neuroscience TraditionalWriting Chinese ... materials Causality Free Full Health Members package LinuxRed Probability sciences Hatof the ... managem... package manage... Distance theorists Open University education i... Government Money of the Articles to be merge... Un... Employment School qualifications Industrial Theory compensat... Mental content of computation automation media Packaging IBM storage History ofdevices computing... History of software Units of angle Causal inference Engineers Sensors Russian mathematicians Programming Central processing u... Health Aid care Inductive 1981 reasoning introductions Educational institut... ... 1789 establishments ... Self-referenceidiomsInstruction Automation processing Microprocessors http://data.linkeded... ChinesePrinting inventions http://data.linkeded... materials Physical exercise Emergency telephone 1969 establishments Buildings and struct... Paper art Former Medicine Eastern Primary care ... Exempt Ortho... charities Building Middle States Associ... Electricity Style (fiction) MIPS 1968 introductions Technologies Archive Distance formats Association education i... of Commo... http://data.linkeded... Real estate Electric current Ballistics Theatre Public Nursing International services Support develo... groups Charities based in B... Charities based in S... Traditions Combinatorics Argumentson words http://data.linkeded... Alchemical processes Culture jamming Performance Measure art tech... theory Television technology Finite rings Integral calculus Digital imaging Instruction set arch... Ceremonies Graduation Articles with exampl...Metalogic Science occupations Computer-aided Domain-specific design prog... Internet radio Languages Literature Digital geometry InternetPeercasting Linguistic research broadcasting Corpus Engineering discipli... Art materials Psychiatry Videocontrover... Trains game genres Physical layer proto... ArtComputer movements Firearm graphics da... terminology Computer engineering Streaming media Internet syst...linguistics television Literary occupations Fiction Writing criticism Microsoft RailWindows transport Criminology Modular arithmetic North Central Continuing Associ... education Electronic engineering Digital television Materials Action Action (genre) Psychiatric video Labeling diagnosis games theory Cloud storage Applications of dist... http://data.linkeded... Philosophical method... Entertainment Political engineering Fiction-writing mode Music Academic administrat... Video on demand serv... Metaphysics Reality Association of Ameri...Behaviorism Analogy argume... http://data.linkeded... Wikipedia articles w... Drug delivery Homogeneous devices chemical... Philosophical Subjects taught in m... http://data.linkeded... Solutions Independent agencies... 1950 establishments Foundations based in... ... Examinations Concepts in aesthetics Nothing Space Dosage forms Organizations establ... Belief Colloidal Physical chemistry chemistry National Science Fou... Musical terminology Environments Simple living Veracity ScienceFunding and technolo... Pittsburgh History &... bodies Psychiatric institut... Macroeconomics http://data.linkeded...Laboratories Elementary arithmetic Approximations Educational institut... History of psychiatry Documents Core issues in ethics Software bugs Universities and col... Anti-psychiatry Medical terms Carnegie Mellon Univ... Social institutions Political culture Oak Ridge Associated... Grammar Theories frameworks of aesthetics Cohort studies Inquiry http://data.linkeded... Integrated Discovery circuits Reliability and invent... Failureengineer... Italian loanwords Printing Healthcare quality Units of time Arts Semiconductor devices Maintenance Syntactic Highertransforma... category theory Rhetoric Dispositional beliefs Geometric shapes Bias Evidence-based Health informaticsmedic... Fractions Philosophical Communalism Social Noam Morphology theories Chomsky theories Informal fallacies Giving Books by type http://data.linkeded... Telecommunications HTML Category Metanarratives Historytheory of sociology Meetings TextbooksLatin words and phra... Fluid dynamics Fluid mechanics http://data.linkeded... http://data.linkeded... Ratios Least squares Interest (psychology)Grid computing Australian inventions Physical cosmology New 21st linguistics Thought Generative century terms Chronology Single equation meth... Theoretical physics Paradoxes Hierarchy Pipingmechanics Continuum Binary operations CheminformaticsString Typingtheory Natural20th Moderncentury philosophy history Employment Millennia Aerodynamics Economics of uncerta... School terminology Functionalism Module theory Public speaking Adulthood Idealism Architectural Wealth design http://data.linkeded... Films by type ge... Multi-dimensional Development Conformity Philosophy of life Empiricism Neuroscience Presentation People in informatio... Skills 3D computer graphics Software requirements Real analysis Academic pressureIndustry in... Construction equipment Infrastructure Computer programmers Education Positive Schoolteachers psychology and traini... National Association... Language Production economics Academic degrees Virtual communities Universities and col... http://data.linkeded... Educators 3Deffects imaging Community organizing Projects Outsourcing Selection Standards-based Construction educ... Calendars Horology Performing http://data.linkeded... Visual Elementary and prima... Definition Order theory Education terminology Design arts High schools and sec... Memory Patent law Population genetics http://data.linkeded... Philosophical logic Engineering occupati... 1801Welfare economics establishments ... Electronic Graphics Education Accounting Research Legal documents Adobe file formats economics terminology Elections institutes entities Legal Systems research... Occupations Marriage School-related terms Individualism SelfExploration Humanities Contemporary Postmodern artart Teaching Project management http://data.linkeded... PatternsYouth Spacetime Vertical transport d... Syntactic entities Standardized tests Economic growth New York Post Alexander Publications Newspapers Engineering Hamilton establi... Economicconcepts published... News Corporation sub... Centimetre%E2%80%93g... indicators Orders of magnitude ... Colonial Happiness Economics ISO 1764 establishments architectur... Government regulat...instituti... standards ofCompanies Campuses http://data.linkeded... Energy Physical quantities SI base units Digital press Time Ethical principles Organizations Massachusetts Doctoral Newbased England Agriculture Institutions Labour Unitedmanagement Change Nations Corporations Private Cultural degrees studies Instit... ... Associat... Political Educational terms law institut... founded... Gener... universities Personal development EmbeddedPlanned systemsscience and ... Corporatism Cohort study methods Emotions http://data.linkeded... Didactics Learning to read Students Motivation Elevators Introductory physics http://data.linkeded... Grammar Fundamental physics ... Qualities of thought Scale model scales Software optimizationScale Utility modeling Standards Democracy Positive Think Forms tanksmental Harvard Titles organizati... Scientific of atti... government University documents Occupations Conductors in music (music) Political science te... Ethics Meaning (philosophy ... Analytic functions Rooms http://data.linkeded... Dynamical systems Computer performance Classical genetics Model aircraft Brown Evidence-based Public Organizational Georgian Health Business Rhodelaw Finance 16th University pract... research Island in...the ... arrondissement Public relations Organisation Corporations universities Theses culture architectur... Page Communication law for Eco... description lan... science Law Remote Customer Help Music performance desk desktop experience Socioeconomics ... http://data.linkeded... Education reform Concurrent computing Higher education Exponentials Risk SchoolsElectronic feedback Educational facilities Psychology Topology Numbers Uncertainty of numbers Mechanical vibrations Filter frequency res... Formal systems Mathematical axioms Educational Regulation Colonial Colleges institut... Social History concepts of ideas Concepts in physics Mathematical analysis Encodings Mathematical proofs Types of International business econom... Non-profit Quality Governance Social assurance en... organizat... anthropology Social psychology http://data.linkeded... Educational stages Television Academia Axiology Mathematics education Wave mechanics Iterative methods Fundraising Professional Budgets titles ... Culture COBOL terminology Polynomials Neuropsychology Sexual arousal University Harvard Mergers of Medical Gothic Academic Chicago Vector graphics Meta-analysis School andRevival acquisit... institutions archi... Role Sociology status of culture Discourse analysis Charles Sanders Peirce Social philosophy Group processes .NET programming lan... Object-oriented Human Sociodynamics prog... Philosophy http://data.linkeded... behavior of language Behavior Training Heat transfer Underwater diving sa... Statistics education Mathematical science... Validity (statistics) Filter theory Mathematical optimiz... Computational fluid ... Polymorphism Biotechnology Committee Systematic Cambridge on Institu... Genetics review or genomics... Identity Computer libraries Summary statistics f... Sexual emotions Greek inventions http://data.linkeded... Compilers Sun Microsystems Sorting algorithms Universities and Professorial col... degrees School types Logic Abstract algebraMathematics Numerical analysis Organizations establ... Home economics Syntactic relationsh... Community Technology Applied linguistics Equations Types of functions Film and video techn... Types of university Engineering ... Control theory http://data.linkeded... Infinity Mind%E2%80%93body pr... Elementary algebra Science education State functions Coding theoryLinear algebra Interpolation Alternative education http://data.linkeded... Algebra Theories of mind Probability distribu... Philosophy of psycho... Human resource manag... Web 2.0 neologisms Local Computer government programming... http://data.linkeded... http://data.linkeded... http://data.linkeded... Production and manuf... Chemical engineering Philosophical concepts Parallel computing Behavioral concepts Mathematical Interdisciplinary fi... http://data.linkeded... Potential concepts Phenomena Phenomenology Sentences by type Operations research Special functions PsychologicalDNA theories Education policy http://data.linkeded... Citizen media http://data.linkeded... Attention-deficit Branches Lexicography hy... of philosophy Differential equations http://data.linkeded... Human-based computat... Attention Psychology articles ... Phase transitions http://data.linkeded... Ecological metrics Oral communication Peer-to-peer computing Manufacturing Ontology http://data.linkeded... Linguistics Semantics http://data.linkeded... Functions and mappings Optimal control Computer storage Culturaldev... File sharing networks Systems engineering Arabic loanwords http://data.linkeded... economics Curricula BehaviouralPerception sciences Population Education by subject Image processing Cryptography Neuroimaging Recording Sound production tec... EvolutionaryUnitsbiology Evaluation Radiology Computer Storage storage media Accountability Learning Business methods theory Consciousness Behavioral and socia... ofEconomics terminology information... Mental processes Concepts in metaphys... Unsolved problems in... sensitiv... Information Object-based http://data.linkeded... Classified information program... http://data.linkeded... Data collection Simulation English words and ph... Brain Integral transforms Optimization Organs algorit... Frequency domain ana... Leadership Academic publishing Programming language... Mathematical structu... Demography BASIC interpreters Physics Wagering Capital Grammatical voices http://data.linkeded... Microsoft BASIC Microsoft Visual BASIC Greek loanwords Stu... compilers Calculus Physical sciences Geometric algorithms Film techniques Electrical circuits BusinessPositions of authority Creativity Concepts Mathematical economics Limbic system Socialsociology Economic economy Management occupations Environmental issues... Management Algorithm descriptio... http://data.linkeded... Procedural programmi... Articles with exampl... http://data.linkeded... Game theory Statistical forecast... http://data.linkeded... Biology theories Theories Emotion Concepts in ethics http://data.linkeded... Group theory Bayesian inference Covariance and corre... Systems psychology Policy DebatingExperimental psychol... Epistemology Human communication Pedagogy Cognition Concepts in epistemo... http://data.linkeded... Error detection and ... Time series analysis http://data.linkeded... Progressive Era in t... MultimediaSocial epistemology BiostatisticsMathematical relations Architects Philosophical school... Video game design Philosophy of educat... Mathematical termino... Western Radioactivity History art of museums American philosophy Educational television Politics by issue Systems Formal methods http://data.linkeded... Science experiments Philosophical moveme... Types of Social sciences organization Branches of psychology Education Translation Arabic words and http://data.linkeded... phr... Normal distribution Mathematical physics Historical History Museum scientifi... of biology collections Sports terminology Pragmatism Writing Social sciences meth... Education-related te... http://data.linkeded... Terminology Metrology http://data.linkeded...Geometry Relationship counsel...Interpersonal relati... Bibliometrics Demographics Political philosophy Government Research Forteana Collecting History of earth sci... development Westerncourt classical mu... http://data.linkeded... Standardization Methods in sociology http://data.linkeded... Educational assessme... Professional Human certifi... Canadian Philosophy system ofEconomies National mind security Consumer behaviour Strategic management Knowledge sharing Length Critical http://data.linkeded... thinking http://data.linkeded... http://data.linkeded... M-estimators Mind Former courts and tr... Economic systems Demographic economics Compiler constructionReference Problem solving Institutes Teleconferencing User interfacesNature Wikis http://data.linkeded... Integrated developme... Statistical terminol... Measurement Support Quality vector United control machi... States federa... ratios Statistical Transportation Video plann... 1993Process (computing) Film production Engineering statistics Hypothesis testing Supply chain managem... Videotelephony Statements Tools introductions Population ecology Adolescence Philosophy of science Greek words and phra... Associative arrays Bioinformatics Accessibility Operating system tec... Structure http://data.linkeded... http://data.linkeded... Article Feedback 5 A... Urban design Ergonomics Sociology index Usability Knowledge Philosophy of mathem... Probability assessment Web analytics ERP Internet software marketing Postgraduate schools http://data.linkeded... Proprietary Data-centric database... program... http://data.linkeded... Programming paradigms Marketing Russian inventions http://data.linkeded... Design of experiments Vector calculus Error Linear programming Gambling terminology P-complete problems Personality theories Mathematical finance Data warehousing Health Social issues Library science Biology Educational technology Programming1992 software language... Object-oriented prog... Systems theory Cybernetics Mental structures Concepts in logic Observation Psychometrics Privacy Acoustics Elementary mathematics Continuous distribut... Convex optimization Business planning Analytics Digital rights User interface techn... Desktopdatabase Microsoft databases... app... Qualitative research Arrays Sociological termino... Literacy History of mining http://data.linkeded... Thought Pharmacokinetics Statistical theory Clubs and societies Financial data analy... Human rights Earth sciences Nonverbal Information Age Organizations communicat... Decision theory Periodic table Abstraction http://data.linkeded... Statistical deviatio... Conditionals Business terms Information technology Interrogative words ... Statistical models Society Anthropological cate... Academic disciplines Mining Neuropsychological Knowledge Psychological testing a... representa... Articles with incons... Regression Bayesian analysis statistics Theory of probabilit... Social groups Programming Classification systems Information Occupational language... safety science ... http://data.linkeded... Diagrams Genetics Cultural history Ecology Collaboration Strategy Process management Computing Mathematical logic http://data.linkeded... Articles with exampl... Sampling (statistics) Signal processing ComputerInnovation occupationsInnovation economics Economics Urban studiesSociolinguistics and pl... American inventions Computer programming Evaluation methods http://data.linkeded... Scientific revolution Planning http://data.linkeded... Actuarial science Resources International relati... http://data.linkeded... Statistical inference Latent variable models Science and technolo... Crowdsourcing http://data.linkeded... Comparison of assess... Information technolo... Reading Analysis Heuristics Sources of knowledge LawLaw enforcement enforcement titles occu... Part-time employment http://data.linkeded... Types of marketing Virtual reality Anthropology Educational software Standards http://data.linkeded... Learning Conceptual models Means Parametric statistics Probability Randomness http://data.linkeded... Dynamic programming Human–computer inter... Microsoft developmen... Market research Medical statistics Product management Publishing Law terms enforcement Ecosystems http://data.linkeded... Complex dynamics Science Business Law enforcement software occu... Personal life Conservation Sociological terms Computing Cognitive science terminology Summary statistics Probability and stat... http://data.linkeded... Educational psycholo... Police ranks http://data.linkeded... Distance education History of Organizational education behav... Futurology Basic concepts Logic in se... http://data.linkeded... Singapore Police Force Formal sciences Source codeScientific method http://data.linkeded... and statistics Tool-using species Questionnaire constr... Learning management ... Human%E2%80%93comput... Vectors Functional analysis Articles containing ... Communication Research methods Cultural landscapes http://data.linkeded... Virtual learning env... Developmental psycho... Decision Expert http://data.linkeded... Support Sys... systems Technical factors of... http://data.linkeded... http://data.linkeded... Megafauna of Australia Hidden Markov models Number theory Places http://data.linkeded... http://data.linkeded... http://data.linkeded... http://data.linkeded... Methodology Environmental science http://data.linkeded... Architectural termin... Probability theory Physical objects http://data.linkeded... Integers Cardinal numbers Zonohedra Prismatoid Space-filling polyhedra polyhe... Critical phenomena Ship construction http://data.linkeded... Cubes http://data.linkeded... Interaction ComputerEpistemology of scie... Mathematical notation Logical consequence Platonic solids Economic anthropology Environment http://data.linkeded... http://data.linkeded... Systems science http://data.linkeded... data Interpretation (phil... Prediction Statistical data sets Estimation theory Forestry Megafauna of Eurasia Personality Volume Social research Sociological theories Technical communicat... Generalized linear m... http://data.linkeded... http://data.linkeded... Aptitude Plants http://data.linkeded... Materials science http://data.linkeded... Natural language pro... InfographicsScientific modeling Mathematical modeling http://data.linkeded... http://data.linkeded... Megafauna Apes Trees of North A... Online gaming Internet Online properties services games ... Information retrieval Artificial intellige... http://data.linkeded... Factorial Cosmopolitan and binomi... species Folksonomy Secure communication http://data.linkeded... http://data.linkeded... http://data.linkeded... Human geography Photo Socialization Risk management Archival science Computer sharing art 1999 introductions Content management s... http://data.linkeded... Reputation management X86-64 Hypertext Linux distrib... Medicinal chemistry Data management Auxiliary sciences o... Econometrics StatisticalSequences methodsand series Real algebraic geome... Megafauna of South Plotting A... software Discrete distributions RiskFacebook Educational video Student analysis ga... Systems culture ecology Groupware Complex Domain systems name system theory Data analysis Plant morphology Linux numerical Numerical anal... programmin... Sensitivity analysis Social Document Network 1988management introductions bookmarking Semantic performance Web %3C!--Professions--%... ... Revolutionary tactics Self-organization Organizational theory Debian-based distrib... Software architecture Intelligence Quality control tools Real numbers Megafauna of Data analysis software Africa Mathematical series Computer-mediated Internet co... access Taxonomy Free software cultur... Mathematical and http://data.linkeded... qua... IRIX software Permutations Computer XML-based Blog Health Security Zoomable network hosting standards promotion sec... services Interoperability User Interf... Mass media DebianPostmodernism Business Poisson intelligence http://data.linkeded... Educational psychology Transdisciplinarity http://data.linkeded... http://data.linkeded... Statistical intervals Probability distribu... Matter C softwarecross-pl... Workflow Symbian Internet Socialtechnology software Virtual privacy constructionism avatars Social systems Media 1993 software technology Psychological attitude English inventions processesPharmacology http://data.linkeded... Psephology Proprietary Companies establishe... Cognitive Performance psychology management Social networks theory Education schoolsStatistical data types Education State schoolsininthe Uni... the... Information systems Categorical data Matrices Logical fallacies Array programming la... Translation Superorganisms Intelligence Video studies Biological 2004 game culture Parsing (inform... systems establishments Cascading Style Sheets Communication Network theory Industrial design Data Data structures Elementary special f... models Windows Mobile Phonecomputers Deliberative methods Algorithms software on strings ... Network addressing Teacher training 1989 introductions Natural sciences Markov Conjugate prior dist... Games of Bada Websites which Types mentalFilmsoftware and mirro... of skill video termi... library Web design Web services Types of databases Application software Reasoning http://data.linkeded... Exponential family d... Software development Human Digital rights byhumanities issue Internet Protocol Hawaiian words and p... Cross-platform softw... trade Computer architecture SoftwareBroadband design Digital E-commerce libraries Stylesheet languages Community buildingInternational Windows word http://data.linkeded... process... http://data.linkeded... Statistics Vector spaces Computational Learning Underlying MUD statis... psychology principle... terminology Social information Articlesp... 1983 in needsoftware of ... Information Articles with exampl... Graphical models Distributions with Megafauna c... Numerical linear alg... Companies Community Symbiosis Home computer Blog websites software software establishe... Notetaking Mac OS Technical X word communicat... proces... Computer graphicsengineering Industrial Dimension Stable distributions Animals described Curves in... Privately RSS servers Proxy Marketing held Global Computer research compa... internetc... comm... security so... Intellectual propert... 1969 introductions Open methodologies Atari ST software Mac OS word processors Quantitative research Quality Collective intellige... Holism Mathematical sciences Machine learning Decision trees Bayesian networks Scottish inventions Estimation of densit... Lifelong learning Computer security Socialsc...networking se... Internet protocols Invasive mammalStatisticsspec... articles ... Deviance Laptops and pr... social ... 2000s in computer Computer law Geography Classification algor... http://data.linkeded... CompaniesAutomaticbased identifica... Digital in media R... Sociology Cloud applications Social Buzzwords media Communication design Experimental physics Data mining Relational database ... Logarithms Representation theor... Environmental health Articles with exampl... BlackBerry Crime software Rights Internet Persistent prevention forum termi... Worlds InternetNeologisms ages InternetWeb 2.0 World Wide Web Prospect http://data.linkeded... theory http://data.linkeded... Charts Data modeling Theoretical computer... http://data.linkeded... Representation theory Web syndication Internet form... architecture Digital technology Enterprise applicati... New media http://data.linkeded... http://data.linkeded... Learning in computer... Bilinear operators Windows software Internet memes Identifiers http://data.linkeded... Algorithms Brand management Documentary Sociocultural film tec...global... http://data.linkeded... Qualia Articles with exampl... Statistical classifi... Service-oriented Computing Speech recognition (bu... platformsScience-related lists Sound Microsoft Office Networks Control flowDigitalProbability photography http://data.linkeded... interpre...http://data.linkeded... Metadata http://data.linkeded... Sparse matrices Assistive technology Analytical chemistry Information technolo... Waves Radiation health eff... http://data.linkeded... History of radio Hearing Mutation Statistical charts a... http://data.linkeded... Euclidean solid geom... Elementary shapes Utility software type Websites Television genres http://data.linkeded... Computational resour...Elementary geometry All articlestheory Computability lacking... SQL http://data.linkeded... One Articles including Metric geometry r... Computer science Articles lacking sou... http://data.linkeded... Complex numbers Web development Database theory Article Feedback 5 Declarative programm... Articles with exampl... Applied mathematics LocalLocal government government dis...in ... http://data.linkeded... Web applications Computational science http://data.linkeded... Places Disk Economics Populated ofplaces Philosophy file systems in Berkshire ... ofest... transpo... disambigu... Relational model http://data.linkeded... Integrals SoftwareHistory companies telecommu... Computer String b...memory similarity me... Area Modernism neuros... Computational Constraint programming Towns in Berkshire Economic geography Sociocultural evolut... Historical eras Query languages Input/output Cloud Companies DOScomputing establishe... on authorities IBM States PC compat... of the United... Northern American co... Reporting ComputersComputer languages Electronic circuit v... Linear operators in ... Unitary Local authorities ... ad...Household Member states ofincome NATO Radio formats Theories of history Globalization Accesshttp://data.linkeded... control Database management ... Epidemiology Multivariate statist... Subdivisions of the...... Markup languages Cloud Online platforms education IBM Website management and AvonCountries PC compatibles Kennet Canal History of television United Countries Income bordering First-level in Country Earth States and bordering ...informati... English-speaking administ... Geographicthe United... Former States Superpowers cou... confederations subdivisions... sciences territori...data ... Identity management School districts... Internet search algo... Cultural geography Visualization (graph... http://data.linkeded... Particle physics http://data.linkeded... Logic in computer sc... Combinatorial optimi... 1776 establishments Data modeling langua... Justification G8 nations Countries borderingdensity Population Income countr... Bicontinental ... Search engine optimi... Google http://data.linkeded... http://data.linkeded... Logging Thermodynamic entropy Library cataloging a... Algebraic structures Analytic geometry Computational comple... Internet companies o... Link analysis Programming language... Pharmaceutical indus... Internet properties ... http://data.linkeded... Databases Data types Secondary education Real-time web Philosophy of therma...Statistical natural ... Combinatorics Privately Twitterheld compa... Cartography http://data.linkeded... Geometric measurement 2006 establishments Companies based ... inFree S... Systemic Risk - Beha... Collaborative software Spam filtering Free educational learning sof... suppor... Internet culture Online chat http://data.linkeded... Free learning manage... Open problems Free software layer pr... systemshttp://data.linkeded... Recommender Application Multiple choice Subroutines Free Free content managem... Programming University constructs of Cambri... software progra... Internet forums Emerging technologies Computational lingui... GraphArtificial theory intellige... Computer networking World Wide Web Conso... Files Computer file systems http://data.linkeded... Youth rights Telecommunications e... Clinical research Symmetry Types of communities Vision Inter-process commun... http://data.linkeded... http://data.linkeded... Markov processes NP-complete Graph families Perfect graphs problems Photography Non-parametric stati... in Graph 1971Differential computerconnectivity sci... topology English Listed Heritage buildings inof...the U... Computer security Complexity Parity classes Archaeology Applied psychology Maps Exploratory data ana... Experiments Graph data structures British architecture Town and country pla... http://data.linkeded... Matrix Differential normal Singular valueformsgeometry decom... Aesthetics Consensus reality Graphic design ClusterGeostatistics analysis Geodesy Stochastic processes Glossaries Manifolds of mathem... Educational research Matrix theory Text messaging Algebraic graph theory Chemical kinetics Survey methodology Types of polling Environmental moveme... Robust statistics Coordinate systems Neural networks French loanwords Member states of the... Ren%C3%A9 Descartes Lie algebras Graphical user Android inter... IOS software software G20 nations Lie groups Geometric topology Set families Companies listed on ... Federal countries System administration Services management ... Technology in society Computer file formats http://data.linkeded... Liberal democracies http://data.linkeded... Server hardware Servers (computing) Nursing South Asian countries VariableSoftware (computerindustry p... GUI game Video widgets gameplay Software licenses Food and Drugresearch Admini... Article Feedback Bla... Business models Statistical outliers user inter... Internet search History engi... of the Inter... 1985 software DrugClinical discovery trials Member states India of the... Software Computer networks distribution Graphical Video game terminology Building Advertising engineering publicat... States and territori... G15 nations Computer jargon http://data.linkeded... Java platform software Member states of the... Countries BRICS the Ind... Statistical programm... Former British colon... Statistical software Blogging Words coined in the ... Software engineering Literary genres Free algebraicgroup Geometric struc... theory Politics and technol... Combinatorial Propertiesgroup ... of groups International rankings Systems Unified Modeling Modeling Lan... Matrix decompositionsOpen formats Lan... Blogs Australian televisio... Internet terminology Thermodynamics Non-standard Ethernet http://data.linkeded... Humans Fundamental analysis Stock market Binary arithmetic analysis English-language Kohlberg Kravis tel... Robe... Network HTTP protocols Free software Rotation Oracle Model compan... selection acquisitions Seven Network Web browsers Tasks Foreign of exchange Derivatives Natural lan... mar... (finance) Google Earth Surfaces Pi Networking hardware .NET2002 software framework Television channels ... Asymptotic analysis Navigation Commodities Modelstranslation Computer-assistedoftr... computation market Units History ofLexical Angle of information mathematics Software 2005units Words that uses Qt software Analysis of algorithms Machine Concurrency Formal (compute... specification... Linux Geometric software variable Regression Orientation centers Field theory ... Software development... http://data.linkeded... Petri nets applicatio... Microsoft Binary Temperature treesSoftware Astrological companies Triangle aspects b... centers Trees (data structur... GPS Mathematics Remote of Keyhole infin... Markup sensing GIS Langu... fileTravel formats Private equity portf... Units Bilinear Differential of linguistic ...forms Open geometr... Alliance Data serialization f... BigTable implementat... Companies establishe... Nucleic acids Affine geometry Virtual Primitive Circles Freeware globes types History ofClassical calculusmechanics Orbits Mac OS X software Celestial Kinematics Conic mechanics sections Software Distributed computin... Euclidean Companies geometry based in S... Project development... management s... Software usingprogramm... Freedesktop.org Application the M... Free Operating Freegraphics systems software windowing X Window systems System http://data.linkeded... Computer hardware co... Spreadsheet Mac OS softwaresoftware Cloud computing Computer prov...o... companies Signs Inventory of death Enterprise modelling Composting Business Anaerobic processwaste Biodegradable digestion Articles containing ... ... Perimeter security Telecommunication th... Discrete mathematics Network architecture 1969 in computer WaterHydrology waveshazards Spreadsheet file file for... Directed graphs sci... Water Sociological streams Weather theory Bibliography fo... Historiography Floodlandforms Fluvial Weather PresentationXML layer p... BasicWater Geomorphology Rivers Postmodern theory meteorological... http://data.linkeded... Composite National Collier 1975 Medal data of IBM Trophy types recip... establishments Te... Electronics ... companie... 1896Semiconductor establishments compan... ... Windows Olympic administration Children sports Computer storage Display Companies American Information com... technology Social UML theory c... classes Companies establishe... brands Partners establishe... Safety codes Stairways Socialism Abstract compan... data types Childhood MacArchitectural OS user interface elements Multinational 1911 Publicly ofComputer Companies Point traded establishments sale comp... security listed compan...on ... so... Figure Ice Sports skating entertainment Garden features dancing Companies Social Microsoft Software based divisions Companies in...W... companies b... establishe... Dow Companies Transaction Jones Companies based processing Industrial... in the Dow... in R... Blogospheres Solid mechanics Hacking Property se... (computer Web security exploits Deformation Injection exploits Vitaceae Computer Viticulture Property security Grape law ex... varieties Social inequality Software Security testing compliance WoodUniv... Alumni of Woodworking Keele The People Pogues 1955 from births Stoke-on... members English guitarists English People Living associated banjoists peoplewi... Woodcarving Figure 5: Topic coverage of LAK data graph for the individual resources. 5. RELATED WORK [3] G. Cobo, D. García-Solórzano, J. A. Morán, E. Santamaría, Cobo et al.[3] presents an analysis of student participation in on- C. Monzo, and J. Melenchón. Using agglomerative line discussion forums using an agglomerative hierarchical clus- hierarchical clustering to model learner participation profiles tering algorithm, and explore the profiles to find relevant activ- in online discussion forums. In Proc. of the 2nd International ity patterns and detect different student profiles. Barber et al. [1] Conference on Learning Analytics and Knowledge, LAK uses a predictive analytic model to prevent students from failing ’12, pages 248–251, New York, NY, USA, 2012. ACM. in courses. They analyze several variables, such as grades, age, [4] A. Essa and H. Ayad. Student success system: risk analytics attendance and others, that can impede the student learning.Kahn and data visualization using ensembles of predictive models. et al. [7] present a long-term study using hierarchical cluster anal- In Proc. of the 2nd International Conference on Learning ysis, t-tests and Pearson correlation that identified seven behavior Analytics and Knowledge, LAK ’12, pages 158–161, New patterns of learners in online discussion forums based on their ac- York, NY, USA, 2012. ACM. cess. García-Solórzano et al. [6] introduce a new educational mon- [5] E. Gabrilovich and S. Markovitch. Computing semantic itoring tool that helps tutors to monitor the development of the relatedness using wikipedia-based explicit semantic analysis. students. Unlike traditional monitoring systems, they propose a In Proc. of the 20th international joint conference on faceted browser visualization tool to facilitate the analysis of the Artifical intelligence, IJCAI’07, pages 1606–1611, San student progress. Glass [8] provides a versatile visualization tool to Francisco, CA, USA, 2007. Morgan Kaufmann Pub. Inc. enable the creation of additional visualizations of data collections. [6] D. García-Solórzano, G. Cobo, E. Santamaría, J. A. Morán, Essa et al. [4] utilize predictive models to identify learners aca- C. Monzo, and J. Melenchón. Educational monitoring tool demically at-risk. They present the problem with an interesting based on faceted browsing and data portraits. In Proc. of the analogy to the patient-doctor workflow, where first they identify the 2nd International Conference on Learning Analytics and problem, analyze the situation and then prescribe courses that are Knowledge, LAK ’12, pages 170–178, New York, NY, USA, indicated to help the student to succeed. Siadaty et al.[13] present 2012. ACM. the Learn-B environment, a hub system that captures information [7] T. M. Khan, F. Clear, and S. S. Sajadi. The relationship about the users usage in different softwares and learning activities between educational performance and online access routines: in their workplace and present to the user feedback to support future analysis of students’ access to an online discussion forum. In decisions, planning and accompanies them in the learning process. Proc. of the 2nd International Conference on Learning In the same way, McAuley et al. [9] propose a visual analyt- Analytics and Knowledge, LAK ’12, pages 226–229, New ics to support organizational learning in online communities. They York, NY, USA, 2012. ACM. present their analysis through an adjacency matrix and an ad- [8] D. Leony, A. Pardo, L. de la Fuente Valentín, D. S. justable timeline that show the communication-actions of the users de Castro, and C. D. Kloos. Glass: a learning analytics and is able to organize it into temporal patterns. Bramucci et al. [2] visualization tool. In Proc. of the 2nd International presents Sherpa an academic recommendation system to support Conference on Learning Analytics and Knowledge, LAK students on making decisions. For instance, using the learner pro- ’12, pages 162–163, New York, NY, USA, 2012. ACM. files they recommend courses or make interventions in case that [9] J. McAuley, A. O’Connor, and D. Lewis. Exploring students are at-risk. reflection in online communities. In Proc. of the 2nd In the related work, we showed how different perspectives and International Conference on Learning Analytics and the necessity of new tools and methods to make data available and Knowledge, LAK ’12, pages 102–110, New York, NY, USA, help decision-makers. 2012. ACM. [10] P. N. Mendes, M. Jakob, A. García-Silva, and C. Bizer. 6. CONCLUSION Dbpedia spotlight: shedding light on the web of documents. In this paper we presented the main features of the Cite4Me Web In Proc. of the 7th International Conference on Semantic application. Cite4Me makes use of several data sources to provide Systems, I-Semantics ’11, pages 1–8, New York, NY, USA, information for users interested on scientific publications and its 2011. ACM. applications. [11] B. Pereira Nunes, S. Dietze, M. A. Casanova, R. Kawase, Additionally, we provided a general framework on data discov- B. Fetahu, and W. Nejdl. Combining a co-occurrence-based ery and correlated resources based on a constructed feature set, and a semantic measure for entity linking. In ESWC, 2013 consisting of items extracted from reference datasets. It made pos- (to appear). sible for users, to search and relate resources from a dataset with [12] B. Pereira Nunes, R. Kawase, S. Dietze, D. Taibi, M. A. other resources offered as Linked Data. Casanova, and W. Nejdl. Can entities be friends? In For more information about the Cite4Me Web application refer G. Rizzo, P. Mendes, E. Charton, S. Hellmann, and to http://www.cite4me.com. A. Kalyanpur, editors, Proc. of the Web of Linked Entities Workshop in conjuction with the 11th International Semantic 7. REFERENCES Web Conference, volume 906 of CEUR-WS.org, pages 45–57, Nov. 2012. [1] R. Barber and M. Sharkey. Course correction: using analytics to predict course success. In Proc. of the 2nd International [13] M. Siadaty, D. Gašević, J. Jovanović, N. Milikić, Z. Jeremić, Conference on Learning Analytics and Knowledge, LAK L. Ali, A. Giljanović, and M. Hatala. Learn-b: a social ’12, pages 259–262, New York, NY, USA, 2012. ACM. analytics-enabled tool for self-regulated workplace learning. In Proc. of the 2nd International Conference on Learning [2] R. Bramucci and J. Gaston. Sherpa: increasing student Analytics and Knowledge, LAK ’12, pages 115–119, New success with a recommendation engine. In Proc. of the 2nd York, NY, USA, 2012. ACM. International Conference on Learning Analytics and Knowledge, LAK ’12, pages 82–83, New York, NY, USA, [14] C. van Rijsbergen, S. Robertson, and M. Porter. New models 2012. ACM. in probabilistic information retrieval. 1980.