=Paper=
{{Paper
|id=Vol-2903/IUI21WS-HUMANIZE-1
|storemode=property
|title=Adaptive Business Data Visualizations and Exploration: A Human-centred Perspective
|pdfUrl=https://ceur-ws.org/Vol-2903/IUI21WS-HUMANIZE-1.pdf
|volume=Vol-2903
|authors=Christos Amyrotos,Panayiotis Andreou,Panagiotis Germanakos
|dblpUrl=https://dblp.org/rec/conf/iui/AmyrotosAG21
}}
==Adaptive Business Data Visualizations and Exploration: A Human-centred Perspective==
https://ceur-ws.org/Vol-2903/IUI21WS-HUMANIZE-1.pdf
Adaptive Business Data Visualizations and
Exploration: A Human-centred Perspective
Christos Amyrotosa,b , Panayiotis Andreoua,b and Panagiotis Germanakosc,b
a UCLan Cyprus, University Ave 12-14, Pyla 7080, Cyprus
b InSPIRE Center, Agamemnonos 20, Pallouriotissa, Nicosia 1041, Cyprus
c UX S/4HANA, Product Engineering, IEG, SAP SE, Dietmar-Hopp-Allee 16, 69190 Walldorf, Germany
Abstract
Today’s business environments are characterized by an indisputable growth in the volume, complexity
and multivariate nature of business processes, data structures and sources. For the business end-users,
this is many times an overwhelming and demotivating experience when interacting with rich business
data visualizations and scenarios. As they need to explore demanding use cases, create fast an under-
standing and make informed decisions so to meet their business goals. This position paper addresses
this challenge by introducing a human-centred model that consists of four main dimensions: User, Vis-
ualizations, Data, and Tasks, and which is maintained at the core of an adaptive data analytics platform
in the business domain. The aim is two-fold: To provide (a) best-fit representation of data for the unique
end-users, and (b) personalized and transparent path of exploration towards accomplishing purposeful
end-to-end business activities. Thus, enabling explainable and intuitive interactions for accurate deci-
sion making and problem solving – saving time and costs.
Keywords
Adaptation, Personalization, Human Factors, User Modelling, Artificial Intelligence, Business Analytics,
Data Visualizations
1. Introduction ing complex patterns. However, according to
IBM, every day we create 2.5 quintillion bytes
Modern business intelligence and data ana- of data – so much data that 90% of all the
lytics platforms use real time visual analytics data in the world today has been created in
to continuously monitor and analyze business the last two years alone [1]. These data come
transactions and historical data so to facil- from a variety of sources and in diverse for-
itate real-time decision support. The result mats, both structured and unstructured, cre-
of this process is then exported into various ating a business ecosystem that brings new
standard format artifacts (e.g., tabular forms, insights but also generates a number of com-
graphs, etc.) offering customization options plications and problems (e.g., delays in real-
to end-users as means for (visual) data ex- time processing, ineffective delivery of multi-
ploration for obtaining insights and unveil- purpose information). As a consequence, this
Joint Proceedings of the ACM IUI 2021 Workshops, April
may disorient end-users that need to navi-
13–17, 2021, College Station, USA gate and take decisions faster than ever when
" camyrotos@uclan.ac.uk (C. Amyrotos); performing their daily business activities us-
pgandreou@uclan.ac.uk (P. Andreou); ing data analytic solutions. Although such
panagiotis.germanakos@sap.com (P. Germanakos)
~ http://scrat.cs.ucy.ac.cy/pgerman (P. Germanakos)
platforms may provide data visualizations that
are considered more usable than others [2],
© 2021 Copyright © 2021 for this paper by its authors. Use
permitted under Creative Commons License Attribution
often their recipients (i.e., the decision mak-
CEUR
4.0 International (CC BY 4.0).
CEUR Workshop Proceedings ers) are overloaded from the vast amount of
http://ceur-ws.org
(CEUR-WS.org)
Workshop ISSN 1613-0073
Proceedings
visual information, which in turn severely de- 2. Background Work and
creases their ability to efficiently assess situ-
ations and plan accordingly [3, 4]. It is ev-
Motivation
ident that current business data exploration Today, with the growing expectations of busi-
and most of data visualizations are: (i) cre- ness end-users and the proliferation of het-
ated based on task and/or data-driven mod- erogeneous business processes and datasets,
els and methods; (ii) extracted based on data traditional approaches for data interpretation
mining algorithms that do not consider any and visualization often cannot keep pace with
role-based specifications and/or user needs the continuous escalating demand, so there
and requirements; and (iii) following an one- is the risk of delivering unsatisfactory and
size-fits-all approach, presenting the same vis- misleading results. Business data models and
ualization type and content to all users ir- processes characterized by significant com-
respective of their needs, requirements, and plexity, making the analysis and understand-
unique characteristics. ing of data by managers, data analysts, busi-
This position paper argues that the com- ness experts, etc., challenging, time consum-
plex nature of business processes, tasks, ob- ing, if not many times impossible. In many
jectives and many data visualizations makes cases, a single activity combines even custom-
it indispensable to include human intelligence made developments (e.g. using Excel) for the
in the data analysis and visualization process subsequent execution of steps creating a dis-
at an early stage. It is vital to enrich the cur- persed, inconsistent and error-prone reality.
rent business analytic platforms with adapta- Hence, it is widely accepted that the increas-
tion techniques and new possibilities for in- ingly large amount of data requires novel, seam-
teractions that will bring the human-in-the- less, transparent and user-friendly solutions
loop by considering the end-users’ individual [5]. As such, handling, analyzing and gain-
differences and their business context (e.g., ing insights into these large multivariate pro-
role, purpose, requirements, tasks) in combi- cesses and datasets through interactive visu-
nation. It proposes a human-centred model alizations is one of the major challenges of
(as the main component of an intuitive data our days [6, 7].
analytics platform), that is composed of four In recent years, many powerful computa-
main dimensions: User, Visualizations, Data tional and statistical tools have been devel-
and Tasks, and considers human factors like oped by various organizations in the business
perceptual preferences, cognitive capabilities sector, such as SAS Visual Analytics1 , IBM
in information processing, affective states, do- Analytics2 , Microsoft Power BI3 , SAP Busines
main expertise, experience, etc., amongst oth- Business Intelligence Platform 4 , Tableau Busi-
ers. Ultimately, the goal is to enable human- ness Intelligence and Analytics5 , Qlik Busi-
centred adaptive data visualizations that will ness Intelligence6 , etc., offering a number of
facilitate explainable exploration and trans- solutions like interactive maps, charts, and
parent analysis of complex and multivariate infographics, visual business intelligence anal-
business processes and datasets, and will sup-
port and enable more effective decision mak- 1 https://www.sas.com
ing on critical business tasks. 2 www.ibm.com/analytics/us/en/technology/products/cognos-
analytics/
3 https://powerbi.microsoft.com/en-us/
4 https://www.sap.com/products/bi-platform.html
5 http://www.tableau.com
6 http://www.qlik.com
ysis, recommend actions, etc. Interestingly [12, 13]; how individuals’ cognitive styles, like
enough, these applications are currently de- Field Dependent-Independent, impact inter-
signed to execute the same operations follow- actions with various information visualiza-
ing a pure machine learning approach (based tions and in relation to individual aid choices
on data models and rigid tasks and objectives) and preferences [14]; or how effective are emo-
and with power users (e.g. data analysts) in tion-triggered (e.g., boredom and frustration)
mind. They embrace the power of the sta- adaptation methods for visualization systems
tistical methods to identify relevant patterns, [15]. Hence, although significant effects have
typically without human intervention. Inevi- been shown in domains like public facing ap-
tably, the danger of modeling artifacts grows plications, educational and navigation con-
when end-user comprehension and control tents, or health datasets, these ideas have rarely
are not incorporated. To this end, although been applied, to our knowledge, to the busi-
modern business intelligence and data ana- ness sector despite the encouraging results of
lytics platforms offer vast repositories of data prior studies [16]. The current position pa-
analysis tools and myriads of customizable per addresses this research gap by highlight-
visualizations; they have not kept up to the ing the effect of a multi-dimensional human-
challenge when it comes to their dynamic ad- centred model in data visualizations and ana-
aptation and personalization depending on the lytic applications that facilitate the execution
role, experiences, intrinsic characteristics or of specific end-to-end business scenarios and
abilities of end-users and still follow a one- tasks. The overarching innovation lies upon
size-fits-all paradigm. This poses an issue as (a) the generation of knowledge and theory,
the effectiveness of a visualization in terms of rules, adaptive interventions, personlization
usability and understanding differs amongst conditions and explanations triggered by the
users [2]. The vast amount of visual uncer- joint influence of cognitive and affective char-
tain information overwhelms the user’s per- acteristics on business data visualizations and
ception, which in turn, severely decreases their exploration, and (b) the development of com-
ability to understand the data and make de- putational techniques, tools and methods that
cisions [3, 4]. will put the theoretical model into practice
On the other hand, the joint benefits of ad- considering the requirements, constraints and
aptation and personalization, and data visu- policies of real-life business settings.
alizations and exploration that consider spe-
cific human factors in the core of their user
models have been highlighted repeatedly in 3. A Proposed
a variety of fields and applications, mostly in Human-centred Model
academia. Indicatively, research works have
identified noteworthy associations of users’ This complex nature of information visuali-
cognitive abilities like perceptual speed, in zations necessitates the development of a com-
relation to performance, accuracy, and satis- prehensive theoretical model that captures im-
faction when interacting with alternative da- portant factors, such as users’ cognitive char-
ta visualization [8, 9]; others focus on opti- acteristics, affect, domain expertise and expe-
mizing data visualizations based on the users’ rience, as well as understanding of the end-
goal, behaviour, cognitive load and skills [10, user roles, objectives, context and the charac-
11]; investigate how human factors like per- teristics of the data [16, 17]. These factors can
sonality and working memory affect user per- be utilized within the data analysis and vis-
formance when interacting with visualizations
with regard to their applicability in specific
business settings and actions optimizing cur-
rent multi-dimensional human-centred user
models [18] that may consider factors like per-
ceptual and cognitive processing characteris-
tics – have an effect on the complexity of the
content regarding users’ task performance, over-
all efficiency and cognitive control of infor-
mation [19], for problem solving and com-
prehension during the interaction process; af-
fect (or affective states) – referring at some
extent to Emotional Arousal and Emotion Reg-
ulation, influencing people’s performance, judge-
Figure 1: Proposed Human-centred Model ment and decision making process [20] while
interacting with data visualizations; domain
expertise and experience – directly related to
ualization process to enable powerful adap- graph comprehension, accuracy and perfor-
tation techniques generating more effective mance of users when interacting with graph
interactions. In this respect, the following tasks as well as to user preference [11], sat-
theoretical model is proposed (see Figure 1), isfaction and the capability of being famil-
comprised from four main dimensions: User, iarized or switching between graphs to ob-
Visualizations, Data and Tasks, which will be tain information; and business role – a person
used as the main driver for further develop- or an entity that is defined by specific objec-
ment and realization. tives, responsibilities and tasks and is the one
that makes decisions and triggers a process,
3.1. User or specific activities, using one or more busi-
ness scenarios of an organization. Data visu-
This dimension is the central point of our en- alizations should be adjusted to the require-
deavour, referring on one hand to the under- ments of each role aligned to the variability
standing of the business users’ roles, nature of tasks, level of knowledge, constraints, etc.,
and their contexts of functioning and interac- conveying the adequate information, when
tion, and on the other hand to the definition and how it is needed, and on the expected
of the human cognitive and affective states breadth and depth that could support and fa-
and their transitions during the interaction cilitate a fast and accurate decision making;
process with data exploration and visualiza- along with the more static ones (e.g. name,
tions. As such, various interventions and adap- age, education, etc.)
tive conditions may be proposed restructur-
ing the respective contents and functionality
to the needs and abilities of users, e.g., pre- 3.2. Visualizations
senting more explanations, additional navi- Data visualizations are most often used to con-
gation support and clarity, reducing the num- vey some meaning out of data and to com-
ber of simultaneously presented stimuli and municate information. Currently, there are
the volume of content. More specifically, build- different types of visualizations (e.g. graphs,
ing upon previous research (see section 2), a plots, tables, etc.) which are used interchange-
number of human factors will be investigated ably depending on the scope and the needs of
a task. For example, the typical bar and col- outcomes/ messages. At the same time, main
umn charts are some of the most used visual- concern is to co-op with the risk of uncer-
ization techniques for comparing data across tainty and data quality derived from situa-
categories (single or multiple), since in a co- tions where not only the types of data or fea-
ordinate system the occurrence of a value is tures can be different, but there is also a vari-
compared directly to its neighbours; or the ety of uncontrolled effects (e.g. dependency
line charts show a connection of data points to data acquisition organizations typically re-
in a coordinate system generating a sequence side), that could hinder the more competent
of values which is used to view trends and discovery of patterns and useful information
cycles over a period of time. Visualizations that in turn could enable a more effective de-
that have some common and comparable fea- cision making. The mechanisms that will be
tures, a recognizable impact of individual dif- considered at this stage will provide high qual-
ferences on them, and apply at a large ex- ity business knowledge that will also deter-
tend in the business domain will be qualified. mine (based on their properties) the signifi-
Once data visualizations are defined, they and cance of the data objects and the yielded adap-
their sub-optimal counterparts will constitute tive data visualizations. This dimension will
a number of subsequent objects which will be make sure that data integration is possible,
enriched with metadata (semantic augmen- by means of intelligent pre-processing and
tation) enabling the filtering process accord- fusion of data; to render data from different
ing to the human-centred model and the data locations or in different types so to be com-
attributes and structure. Thereupon, adapta- parable, and to create mappings among fea-
tion and personalization techniques will be tures so that integrated data analysis will be
crafted to offer: (a) Dynamic alteration of the possible. Several unaddressed issues will be
content presentation and hierarchical struc- tackled in supporting data analysis of busi-
ture of data visualization attributes (e.g., re- ness datasets especially through the use of
ordering, salience, size, saturation, texture, visualization, such as (a) very large, i.e., scal-
color, orientation, shape, etc.); (b) provision ability, (b) dynamic, i.e., addressing the ve-
of various navigation tools and support (e.g., locity aspect within the V’s of Big Data, and
visual prompts, explanations) for data/ visual (c) heterogeneous, i.e., consisting of differ-
exploration during end-to-end business tasks ent data types both in terms of acquisition
execution; (c) variable amount of user con- method and representation [21].
trol (e.g., allowing further (deeper) data ex-
ploration); and (d) additional assistive tools 3.4. Tasks
(e.g., data properties and details), etc.
Business tasks refer to role-based units of work,
as a sequence of actions, undertaken by the
3.3. Data
end-users. They are usually part of a wider
A big challenge currently for the research com- constellation of business activities and pro-
munity, is to develop intelligent data mining cesses that are executed with the purpose of
mechanisms that can support the efficient ex- accomplishing a specific business goal (e.g.,
traction and fusion of multivariate data from define/ maintain material and external ser-
different locations, their integration into a uni- vices demand, or oversee stock, material de-
fied information model so that it can seam- mand and supply). Transparency, explainabil-
lessly support exploratory data analysis for ity and support of end-to-end tasks execution
understanding, interpreting and modelling the is a big challenge currently in the business
domain, as users many times strive to un- tions and explanations? How to design and
derstand the flow, dependencies and contents develop transparent and personalized condi-
of multi-variate information (usually gener- tions that can ensure seamless end-to-end data/
ated by different business processes and data visual exploration support? What kind of com-
models) while at the same time are not in- putational intelligence algorithms need to be
cluded in the subsequent decisions that lead developed to ensure data integration and fu-
to a result or to actionable knowledge. Hence, sion of various dispersed datasets/ sources?
recognizing the essential role of the end-user How to verify the validity of the theoretical
in the data visualization and exploration pro- human-centred user model? Subsequently, a
cess, it is important to enable effective human rigorous methodological approach need to be
control during the tasks execution by extend- embraced, following an incremental design
ing the usability and usefulness of compu- and development iterative process. The pro-
tational process models and visual analytic posed theoretical model will guide the imple-
methods to gain insights and value out of the mentation of an intuitive data analytics plat-
data towards informed business decision mak- form that will dynamically adjust (i.e., offer-
ing. In this respect, machine learning tech- ing alternative representations) to the unique
niques may be employed for analyzing big end-users characteristics, data structure and
datasets arising from complex business pro- semantics of data visualizations, and explo-
cesses and scenarios, for e.g., discovering pat- ration tactics derived from the various busi-
terns in data simulations or for modelling un- ness data sources/ processes of an organiza-
certainties increasing transparency of tasks tion.
execution (e.g. change of a product’s demand).
Additionally, many problems in the business
area can be formulated as probabilistic infer- 4. Expected Benefits and
ence problems. Thus, a focus on probabilistic- Impact
based data mining methods, including graph-
based data mining, topological data mining Given the users’ diversified individual differ-
and other information-theoretical-based ap- ences in cognitive processing, affect, percep-
proaches (e.g., entropy-based), as well as on tual preferences, role, requirements, needs,
the human-in-the-loop concept for increas- and expertise, as well as the size, diversity
ing explainability while users interact with and processing overhead of big business data
respective business use cases will be consid- sets, it is expected that this research will yield
ered. flexible best-fit data visualizations and explo-
It is apparent that the successful realiza- ration methods that will support the unique
tion of the above human-centred model ad- end-users with the expected transparency and
heres to a number fundamental research ques- explainability during an end-to-end interac-
tions that need to be addressed, such as: Which tion. The suggested adaptive interventions
parameters and human factors are considered build on the premise that graphics and text
significant so to define an inclusive human- have a complementary role in information pre-
centred user model in the context of business sentation – while graphics can convey large
data visualizations? What, how and when amounts of data compactly and support dis-
data visualizations content can be enriched/ covery of trends and relationships, text is much
altered and delivered to the end-users? What more effective at pointing out and explaining
adaptation techniques and interventions are key points about the data, in particular by fo-
feasible for generating best-fit data visualiza-
cusing on specific temporal, causal and eval- exploration of data sets and processes. The
uative aspects. Crafting different modalities aftermath is to increase the users’ understand-
not only makes the presentation more engag- ing through explainable visual information as
ing, but could also better suit users with dif- well as their ability to quickly act upon it while
ferent cognitive abilities and affective states. engaging into purposeful transparent explo-
In a broader perspective, the results of this re- rations of end-to-end business tasks.
search work will have a wider business and
economic impact by helping users to compre-
hend and familiarize themselves with usable 6. Acknowledgements
data visualizations adjusted to their knowl-
This research is partially funded by the Cyprus
edge and abilities, enhancing their satisfac-
Research and Innovation Foundation under
tion and acceptability of related end-to-end
the projects IDEALVis (EXCELLENCE/0918/0366)
business workflows and services. Main vi-
and RABIT (START-UPS/0618/0053) and the
sion is that such practices, which provide hu-
European Union under the project SLICES-
man-centered data visualizations and visual
DS (No.951850).
analytic services, will be incorporated in fu-
ture tools and systems, increasing the sup-
port and effectiveness of decision making in References
critical tasks, enabling fast and inclusive ac-
tion plans, and cutting down unnecessary it- [1] IBM, Bringing big data to the enterprise,
erations and costs. accessed on jan. 1, 2020, 2016.
[2] S. Liu, W. Cui, Y. Wu, M. Liu, A sur-
vey on information visualization: re-
5. Conclusion cent advances and challenges, The Vi-
sual Computer 30 (2014) 1373–1393.
A vital requirement for any business that wants
[3] G.-P. Bonneau, H.-C. Hege, C. R. John-
to stay competitive in today’s data driven econ-
son, M. M. Oliveira, K. Potter, P. Rhein-
omy is to use business intelligence platforms
gans, T. Schultz, Overview and state-of-
and data analytics that offer advanced data
the-art of uncertainty visualization, in:
visualizations and exploration capabilities, be-
Scientific Visualization, Springer, 2014,
yond the traditional data-driven filtering (drill-
pp. 3–27.
down) and customization. The objective is to
[4] C. Kinkeldey, A. M. MacEachren,
facilitate end-users (e.g., data analysts, busi-
M. Riveiro, J. Schiewe, Evaluating the
ness experts) during tasks executions to ob-
effect of visually represented geodata
tain insights and unveil complex patterns that
uncertainty on decision-making: sys-
lie within data and processes for making in-
tematic review, lessons learned, and
formed decisions. Accordingly, this position
recommendations, Cartography and
paper proposes a multi-dimensional human-
Geographic Information Science 44
centred model – composed of factors, such as
(2017) 1–21.
users’ roles, cognitive individual differences
[5] F. Research, Becoming an insights-
in information processing, affective states, per-
driven company, accessed on jan. 6,
ceptual preferences, domain expertise and ex-
2020, 2018.
perience – as the theoretical cornerstone of
[6] A. Kerren, J. Stasko, J.-D. Fekete,
an intuitive data analytics platform, that may
C. North, Information Visualization:
offer seamless adaptive data visualizations and
Human-Centered Issues and Perspec- forming adaptive information visualiza-
tives, volume 4950, Springer, 2008. tion support, in: Proceedings of the
[7] A. Kerren, F. Schreiber, Toward the role SIGCHI Conference on Human Factors
of interaction in visual analytics, in: in Computing Systems, 2014, pp. 1835–
Proceedings of the 2012 Winter Simula- 1844.
tion Conference (WSC), IEEE, 2012, pp. [14] B. Steichen, B. Fu, Towards adap-
1–13. tive information visualization-a study
[8] S. Lallé, C. Conati, G. Carenini, Impact of information visualization aids and
of individual differences on user expe- the role of user cognitive style, Fron-
rience with a visualization interface for tiers in Artificial Intelligence 2 (2019)
public engagement, in: adjunct publi- 22.
cation of the 25th conference on user [15] D. Cernea, A. Ebert, A. Kerren, A study
modeling, Adaptation and Personaliza- of emotion-triggered adaptation meth-
tion, 2017, pp. 247–252. ods for interactive visualization., in:
[9] D. Toker, C. Conati, G. Carenini, UMAP Workshops, 2013.
M. Haraty, Towards adaptive infor- [16] T. Poetzsch, P. Germanakos,
mation visualization: on the influence L. Huestegge, Toward a taxonomy
of user characteristics, in: Interna- for adaptive data visualization in
tional conference on user modeling, ad- analytics applications., Frontiers Artif.
aptation, and personalization, Springer, Intell. 3 (2020) 9.
2012, pp. 274–285. [17] B. Mutlu, M. Gashi, V. Sabol, Towards a
[10] B. Steichen, G. Carenini, C. Conati, task-based guidance in exploratory vi-
User-adaptive information visualiza- sual analytics, in: Proceedings of the
tion: using eye gaze data to infer vis- 54th Hawaii International Conference
ualization tasks and user cognitive abil- on System Sciences, ????, p. 1466.
ities, in: Proceedings of the 2013 inter- [18] P. Germanakos, M. Belk, et al., Human-
national conference on Intelligent user Centred Web Adaptation and Personal-
interfaces, 2013, pp. 317–328. ization, Springer, 2016.
[11] D. Toker, S. Lallé, C. Conati, Pupillom- [19] S. Lallé, D. Toker, C. Conati, G. Carenini,
etry and head distance to the screen to Prediction of users’ learning curves for
predict skill acquisition during informa- adaptation while using an information
tion visualization tasks, in: Proceedings visualization, in: Proceedings of the
of the 22nd International Conference 20th International Conference on Intel-
on Intelligent User Interfaces, 2017, pp. ligent User Interfaces, 2015, pp. 357–
221–231. 368.
[12] T. M. Green, B. Fisher, Towards the per- [20] Z. Lekkas, N. Tsianos, P. Germanakos,
sonal equation of interaction: The im- C. Mourlas, G. Samaras, The role of
pact of personality factors on visual an- affect in personalized learning, in:
alytics interface interaction, in: 2010 2009 Ninth IEEE International Confer-
IEEE Symposium on Visual Analytics ence on Advanced Learning Technolo-
Science and Technology, IEEE, 2010, pp. gies, IEEE, 2009, pp. 629–633.
203–210. [21] H. Chen, R. H. Chiang, V. C. Storey,
[13] G. Carenini, C. Conati, E. Hoque, B. Ste- Business intelligence and analytics:
ichen, D. Toker, J. Enns, Highlighting From big data to big impact, MIS quar-
interventions and user differences: in- terly (2012) 1165–1188.