=Paper=
{{Paper
|id=Vol-2068/preface-uistda
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-2068/preface-uistda.pdf
|volume=Vol-2068
}}
==None==
https://ceur-ws.org/Vol-2068/preface-uistda.pdf
Overview of IUI2018 Workshop: User Interfaces for
Spatial and Temporal Data Analysis (UISTDA2018)
Shoko Wakamiya Adam Jatowt Yukiko Kawai
Nara Institute of Science and Kyoto University, Japan Kyoto Sangyo University,
Technology, Japan adam@dl.kuis.kyoto-u.ac.jp Japan
wakamiya@is.naist.jp kawai@cc.kyoto-su.ac.jp
Toyokazu Akiyama Ricardo Campos Takuro Yonezawa
Kyoto Sangyo University, Polytechnic Institute of Tomar, Keio University, Japan
Japan LIAAD INESC TEC, Portugal takuro@ht.sfc.keio.ac.jp
akiyama@cc.kyoto-su.ac.jp ricardo.campos@ipt.pt
ABSTRACT heterogeneous (including texts, images, videos, geographic in-
Nowadays, humanity generates and contributes to form large formation, temporal information, etc.) and large enough to be
and complex datasets, going from documents published on handle with common techniques. Hence, special and dedicated
media outlets, posts on social media or location-based in- solutions to data visualization, analysis and processing need to
formation. The generated information tends to be complex, be proposed. In particular, (1) novel user interfaces that would
heterogeneous (texts, images, videos, etc.) and is growing at assist users in analyzing data from the temporal and spatial
an incredible pace, with much of this data having a strong spa- viewpoints; (2) effective data preprocessing and management
tial and temporal focus. This steady increase in the availability techniques for constructing large scale real-world applications
of such a volume of information, forces the development of or for investigating complex interaction patterns in order to de-
more effective user interfaces that would assist users in effi- tect useful knowledge; and (3) collaborative systems/platforms
cient visualization, analysis and exploration of the data. This for creating or managing large amounts of data having spatial
half-day workshop on User Interfaces for Spatial and Tem- and temporal character (e.g., volunteered geographic systems)
poral Data Analysis (UISTDA) held in conjunction with the are needed to help multiple users effectively collaborate.
IUI2018 conference on March 11th, aimed at sharing the latest
The UISTDA2018 workshop1 held in conjunction with the
progress and developments, current challenges and potential
IUI2018 conference2 , appears in this context to share latest
applications for exploiting large amounts of spatial and tempo-
progress, developments, current challenges and potential ap-
ral data. In this paper we provide an overview of the workshop
plications for exploiting large amounts of spatial and temporal
goals together with its main contributions.
data. In this paper, we introduce the topics discussed in the
workshop and offer a brief overview of the papers presented
Author Keywords therein.
User Interface; Spatial; Temporal; Data Analysis.
The main topics of the UISTDA2018 workshop are that of
supporting user interface research through the practical ap-
INTRODUCTION plication of Computer Science theories or technologies for
Nowadays, humanity generates many large and complex analyzing and making use of various kinds of spatial and tem-
datasets with strong spatial and temporal characteristics. So- poral data, visualizing spatial and temporal data patterns and
cial media services like Twitter, are an obvious example of providing efficient access to the large wealth of spatial and
these datasets offering access to an incredible amount of infor- temporal knowledge, especially from social media, multime-
mation issued in a given location at a particular time period. To dia, human behavior logs, trajectories, etc.
analyze and identify this information and to extract meaning-
In particular papers concerning the following topics (but not
ful and unknown spatial and temporal patterns is not an easy
limited to) were discussed in more detailed during the work-
task. In general, the generated digital data tends to be complex,
shop:
• Natural language processing for spatial-temporal data
• Spatial-temporal human behavior analysis
• User interface for spatial-temporal data analysis
©2018. Copyright for the individual papers remains with the authors. Copying permit-
ted for private and academic purposes. 1 http://sociocom.jp/~event/uistda2018/
2 http://iui.acm.org/2018/
UISTDA ’18, March 11, 2018, Tokyo, Japan
• Discovering spatial-temporal patterns and knowledge CONTRIBUTIONS
Keynote Talk
• Applications with spatial-temporal data
We were pleased to have a keynote talk by Prof. Takuro
• Evaluation metrics for user interface or applications Yonezawa from Keio University, Japan on the topic of “smart
city and smart society”. The title and summary of his talk is
WORKSHOP PROGRAM COMMITTEE
as follows.
The Program Committee of the UISTDA workshop consists Title: Unfold the city: excavation and analysis of latent
of the following researchers: spatial-temporal urban data
Omar Alonso (Microsoft, USA) Summary: Smart city, though there exist several definitions
for it, is defined as a complex ecosystem characterized by
Yutaka Arakawa (Nara Institute of Science and Technology, the intensive use of information and communication tech-
Japan) nologies, aiming at making the cities more efficiency, more
attractive, more sustainable and a unique place for inno-
Eiji Aramaki (Nara Institute of Science and Technology,
vation and entrepreneurship. One promising way toward
Japan)
making city smarter is to understand city deeply and real-
António Branco (University of Lisbon, Portugal) time based on large amount of heterogeneous city data.
However, excepting several social network service data or
Christophe Claramunt (Naval Academy Research Institute, some advanced cities filled with IoTs, acquiring valuable
France) spatial-temporal city data is still the first obstacle to solve
for most of the cities. In this talk, I will present our approach
João Cordeiro (University of Beira Interior, Portugal) of how we leverage existing city resources which exist in
any cities to excavate latent city data, and how we share
Michael Färber (University of Freiburg, Germany) and analyze the data for understand the city, with over-three
years experiments in Fujisawa city, Japan. Furthermore, I
Dhruv Gupta (Max Planck Institute for Informatics, Ger- will discuss further challenges and many opportunities that
many) smart city, and smart society faces.
Péter Jeszenszky (University of Zurich, Switzerland) Research Paper
Alipio M. Jorge (FCUP, Univ. do Porto / LIAAD, INESC A peer-reviewed process was carried out to select the papers,
Porto L.A., Portugal) with at least three members of the Program Committee re-
viewing each paper. This resulted in 5 accepted submissions
Hiroshi Kawasaki (Kyushu University, Japan) (initially 7 were accepted out of 9, but 2 have been with-
drawn): 2 full papers and 3 short papers, that discuss ideas and
Kyoung-sook Kim (National Institute of Advanced Industrial progress on several interesting topics, including urban com-
Science and Technology, Japan) puting, road/city feature extraction, location de-identification,
human behavior and video scene retrieval.
Feifei Li (University of Utah, USA)
Mozaffari et al. [1] present methods for classifying reading be-
Vitor Mangaravite (INESC Porto, Portugal) havior using data gathered from eye tracker equipments. The
classification is done using deep neural networks, specifically,
Bruno Martins (University of Lisbon, Portugal) bi-directional LSTMs. In order to alleviate the lack of data
the authors further propose how to generate synthetic data by
Miguel Mata (UPIITA-IPN, Mexico) training a hierarchical hidden markov model on the ground
truth data.
Sérgio Nunes (INESC TEC and FEUP, U.Porto, Portugal)
Graells-Garrido et al. [3] develop an aggregation-based ap-
Arian Pasquali (INESC TEC, Portugal) proach for the analysis of phone-based trips recorded at the
city level. Particularly, they introduce Mobilicities, which
Panote Siriaraya (Kyoto Sangyo University, Japan) automatically generate travel patterns inferred from mobile
phone network data using NMF, a matrix factorization model.
Taketoshi Ushiama (Kyushu University, Japan)
Probst et al. [4] propose a sketch-based spatio-temporal re-
Yuanyuan Wang (Yamaguchi University, Japan) trieval system for sports. They suggest data schema for spatio-
temporal retrieval and show the web-based user interface. The
Jiewen Wu (Institute for InfoComm Research, A*STAR, Sin- effectiveness of the proposed user interface was evaluated
gapore) through the user study using football and Ice hockey games.
Shohei Yokoyama (Shizuoka University, Japan) Endo et al. [2] propose an interpolation method to suggest
sightseeing spots by aggregating geo-location information for
Yihong Zhang (Kyoto University, Japan) a given target location with the help of surrounding location
bearing tweets. They show results obtained from information Bukhari, and Andreas Dengel. 2018. Reading Type
interpolation and analysis of cherry blossoms in Japan in 2017. Classification based on Generative Models and
Bidirectional Long Short-Term Memory. In Proceedings
Taguchi et al. [5] propose an innovative method for loca- of the first workshop on User Interface for Spatial and
tion de-identification in Twitter messages, based on the use Temporal Data Analysis (UISTDA ’18). CEUR-WS.
of a text classification method capable of automatically as-
signing tweets to the corresponding locations. They use text 2. Masaki Endo, Masaharu Hirota, and Hiroshi Ishikawa.
classification methods for inferring if the location behind a 2018. Utilization of Information Interpolation using
tweet can easily be inferred by an automated method and/or Geotagged Tweets. In Proceedings of the first workshop
by a human expert, and they also advanced a procedure for on User Interface for Spatial and Temporal Data
de-identifying tweets based on removing morphemes until a Analysis (UISTDA ’18). CEUR-WS.
location classifier can no longer estimate the location of the
3. Eduardo Graells-Garrido, Diego Caro, and Denis Parra.
tweet.
2018. Toward Finding Latent Cities with Non-Negative
Acknowledgements Matrix Factorization. In Proceedings of the first
We would like to thank the IUI2018 conference organiz- workshop on User Interface for Spatial and Temporal
ers for letting us organize the UISTDA2018 workshop and Data Analysis (UISTDA ’18). CEUR-WS.
for their assistance. We also thank the PC members for 4. Lukas Probst, Ihab Al Kabary, Rufus Lobo, Fabian
their effort in reviewing and evaluating submitted papers Rauschenbach, Heiko Schuldt, Philipp Seidenschwarz,
as well as paper authors for choosing our workshop. This and Martin Rumo. 2018. SportSense: User Interface for
workshop was partially funded by the ERDF through the Sketch-Based Spatio-Temporal Team Sports Video Scene
COMPETE 2020 Programme within project POCI-01-0145- Retrieval. In Proceedings of the first workshop on User
FEDER-006961, by National Funds through the FCT as part Interface for Spatial and Temporal Data Analysis
of project UID/EEA/50014/2013, by Strategic Information (UISTDA ’18). CEUR-WS.
and Communications R&D Promotion Programme (SCOPE)
#171507010, the Ministry of Internal Affairs and Communica- 5. Katsuya Taguchi and Eiji Aramaki. 2018. Novel Location
tions of Japan, by ACT-I, JST, and by JSPS KAKENHI Grant De-identification for Machine and Human. In
Number JP16K16057. Proceedings of the first workshop on User Interface for
Spatial and Temporal Data Analysis (UISTDA ’18).
REFERENCES CEUR-WS.
1. Seyyed Saleh Mozaffari Chanijani, Federico Raue,
Saeid Dashti Hassanzadeh, Stefan Agne, Syed Saqib