Notes: Submissions to a special session should be submitted by choosing the respective special session when you Submit a Paper to IEEE DSAA'2015. Review will be coordinated by the special session chairs and final decisions will be made by the program co-chairs. Accepted special session submissions will be included into the Special Session part of the main conference proceedings to be published by IEEE and included into the IEEE Xplore Digital Library, EX-indexed.

Please submit your special session papers here.

Special Session on Trends & Controversies in Data Science (TCDS)

Florence ForbesWray Buntine
Inria Rhône-Alpes & Laboratoire J. Kuntzmann, FranceMonash University, Melbourne, Australia

Aims and Scope

As an emerging area, data science is facing great opportunities as well as challenges.Often arguments exist: What is data science? Why data science? We have information science already, why do we need data science? Do we need analytics science? Is analytics new? What is the difference between statistics and data analytics? What makes a data scientist?

We believe that a special session on Trends and Controversy about data science and advanced analytics could bring insights from different mindsets for the healthy development of the science and society. Accordingly, this T&C special session will host talks by invitation to outline different views about today and future of data science. Invited speakers can contribute a paper (in the same format as the main conference submissions but could be less than 10 pages) to the special session, which will be handled by program co-chairs and accepted into the main conference proceeding probably by addressing comments from the program co-chairs.

Topic of Interests

We expect insightful talks about forward-thinking, big thinking, original research, critical reflection and questioning on existing theories and tools, and/or innovative insights about data science, big data, advanced analytics.

Nominations to this T&C special sessions are welcome, please contact

Special Session on Big Behavioral Data Analytics (BBDA)

Peng CuiPhilip S. YuLongbing Cao
Tsinghua University, ChinaUniversity of Illinois at Chicago, USAUniversity of Technology Sydney, Australia

Aims and Scope
With the rapid proliferation of web applications, such as search engine, e-commerce and social networking service, more and more user behaviors are available online, which opens a new perspective for behavioral data analytics where more focus should be put on various types of interactions on the web. For example, users can build friendships with, send messages to and make phone calls with other users, creating user-user interactions; they can also post messages, buy products and check in restaurants, creating user-item interactions. Developing computational methods to model user behaviors, analyze different behavioral patterns, understand mechanisms underlying behavioral logs and eventually predict the next behaviors or detect strange behaviors is of paramount importance since it would improve applications like web search, recommender system and social networking services and, on the other side, stop frauds, spams and attacks. This presents clear challenges to behavior modeling: user behavior depends on contents, intentions and contexts in complex online environments. Moreover, the online settings bring big challenges to behavioral data analysis since user behavioral data is in web scale, heterogeneous, of multiple dimensions, highly sparse and dynamic.

Topics Of Interest:
Methods and techniques:

  • New principles of user behavior formation

  • Modeling personal preference and interpersonal influence

  • Modeling individual behavior and group behavior

  • Modeling temporal behavior and behavioral dynamics

  • Modeling check-in behavior and purchasing behavior

  • Scalable techniques for large-scale behavioral data analysis

  • Efficient techniques for online behavioral processing

Applications of online user behavioral analytics, such as:

  • Social networks

  • Recommender systems

  • E-commerce systems

  • Fraud and spam detection

  • Suspicious behavior detection

  • Search engines

Big Data, Distributed Technologies and Intelligent Agents (BDIA)

Download BDIA call for papers

Session Program Chairs:
Yifeng ZengVladimir GorodetskyAndreas L. Symeonidis
School of Computing, Teesside University, UKSt. Petersburg Institute for Informatics and Automation, Russian Academy of Sciences,RussiaAristotle University of Thessaloniki,Greece

Aims and Scope
It has been a long history that intelligent agent technologies facilitate solutions to data relevant issues such as data management, data mining, information extraction, search, and integration. Agent-based models provide an expedient framework for predicting expansion and evolution of data while distributed agent architectures make it possible to manage heterogeneous data resources. On the other hand, by actively analyzing the input of more and more data sources, intelligent agents can better response to the changing world and further improve their intelligence. For instance, a recommender agent provides desirable service to both purchasers and sellers by retrieving sensible knowledge from the growing data in the e-market.

The emergence of big data poses a series of challenges as well as prospects to both researchers and practitioners in relevant communities such as:

  • computational instability of basic statistical processing algorithms like error accumulation, spurious correlations etc.,

  • computational complexity of big data-driven model design, data management, data mining/machine learning,

  • challenges in social computing, information search and knowledge extraction, etc.

The basic approaches intended to overcome these challenges are specialized algorithms for big data statistical processing, meta-data driven data splitting and dimensionality reduction, nonlinear data transformations intended for data aggregation and data filtering, ontology-driven big data structuring. The most of these approaches realize distributed algorithms that, in many cases, best fit the capabilities of distributed intelligent agent technologies.

A novel big data related issue is big software code analytics. Examples of such tasks are:

  • Identification of reuse practices in distributed, agent-based and service-oriented software development

  • Search-driven software development, based on software semantics and software repositories

  • Mining messages execution traces and logs for improving software quality.

  • System monitoring and fault-detection based on real-time system information.

The special session aims to promote discussions and exchanges of ideas and experience on theories, algorithms, technologies and applications of the synergy between intelligent agents and big data research.

Topics Of Interest:
The special session aims to facilitate discussions on a number of challenging topics on agents-based solutions to big data as well big data-driven agent technologies. In particular, we encourage submissions on, but not limited to:

1. Formal agent-based framework for Big data

  • Agent-mediated parallel/distributed big data management/mining

  • Agent-based simulation models for data visualization,
2. Agent-based architectures for big data model design

  • Agent-mediated data-driven big data ontology design

  • Ontology-driven big data mining and machine learning,
3. Data-driven Intelligent Software

  • Big Code analytics for intelligent (software) design
    Intelligent synthesis of software based on big data analysis
4. Data-driven agent systems

  • Data-driven reasoning and learning

  • Data-driven decision making and planning

  • Data-driven agent interaction and coordination

  • Data-driven personalized agents
5. Surveys and Case studies

Special session on Bioinformatics, Health and Medical Analytics (BHMA)

Jinyan Li
Vincent S Tseng
University of Technology Sydney, Australia
National Chiao Tung University, Taiwan

Aims and Scope:
This session especially looks for submissions which focus on bioinformatics problems and healthcare data analytics techniques. The topics include (but not limited to): (1) genomic sequence assembling, sequence pattern discovery, expression data analysis, structure bioinformatics, molecular network mining, and system biology; and (2) clinical records classification, clinical text clustering, ICU time series modelling, Imaging data processing, and Brain EEG signal analysis. Selected papers will be invited to publish at international journals after extension.

Special Session on Data Oriented Constructive Mining and Multi-Agent Simulation (DOCMAS)

Graduate School of Information Systems, The University of Electro-Communications, JapanIBM T.J. Watson Research Center, USACollege of Information Science and Engineering, Ritsumeikan University, Japan

Aims and Scope
When we try to understand diverse complex systems such as a human brain, social systems, Internet, and WWW, it is not enough to simply dig out knowledges from the vein of data. It is required to establish new "constructive data mining process" consisting of iterative processes of the generation of data veins and exploration of new knowledge from them. The primary aim of this special session is to facilitate the collaboration among researchers on multi-agent simulation (MASim) and data mining (DM). While MASim researchers have simulation and modeling technologies, DM researchers have analytical and knowledge retrieval techniques. There is the complementary relationship between MASim and DM researches so that the ultimate goal of this session is to create new multi-agent research area by synthesizing two different areas.

Topics of interest include:
Multi-Agent simulation is primary technology in Artificial Intelligence. MASim methodologies/technologies have not been sufficiently mature though, its scientific significance is getting quite high to understand and analyze complex large-scale systems, such as human societies. Data mining is another primary AI technology to retrieve hidden information or knowledge from big data. However, real data for the mining does not always include essential elements of a target complex system. Thus, a simulation is promising way to generate meaningful data which is hard to obtain in the real world. We pursue new methodologies and technologies of multi-agent simulationsin conjunction with data mining techniques. This session can be a core meeting for the new research area. The topics listed below are key technologies for MASim and DM, and their applications.

  • Multi-agent simulation

  • Social simulation

  • Simulations on complex network

  • Collective Intelligence

  • Social and economic phenomena in MASim

  • Emergent evolution system

  • Evolution system

  • Human behavior modeling

  • Learning from big data from MASim

  • Knowledge discovery with MASim

  • Cloud computing technology for MASim

  • Big Data analysis

  • Social Media

  • HPC for massively mult-agent simulation

Program Committee (tentative)
Tibor BOSSE, Vrije Universiteit Amsterdam, Netherlands
Alexis DROGOUL, Institut de Recherche pour le Developpement/Can Tho University,Vietnam
Tomoyuki HIGUCHI, The Institute of Statistical Mathematics, Japan
Akihiro INOKUCHI, Osaka University, Japan
Toru ISHIDA, Kyoto University, Japan
Toshihiro KAMISHIMA, National Institute of Advanced Industrial Science and Technology (AIST), Japan
Franziska KLUEGL, University of Wurzburg, Germany
Hiromitsu HATTORI, College of Information Science and Engineering, Ritsumeikan University, Japan
Vipin KUMAR, University of Minnesota, USA
Satoshi KURIHARA, Osaka University, Japan
Toyotaro SUZUMURA, IBM T.J. Watson Research Center, USA
Jiming Liu, Hong Kong Baptist University, Hong Kong
Hideyuki NAKASHIMA, Future University Hakodate, Japan
Nariaki NISHINO, University of Tokyo, Japan
Itsuki NODA, National Institute of Advanced Industrial Science and Technology (AIST), Japan
Mario PAOLUCCI, Institute for Cognitive Science and Technology, Italy
Kosuke SHINODA, National Institute of Advanced Industrial Science and Technology (AIST), Japan
Gaku YAMAMOTO, IBM Software Group, Japan
Hitoshi YAMAMOTO, Rissho University, Japan
Philip S. YU, University of Illinois, USA
Mohammed ZAKI, Rensselaer Polytechnic Institute (RPI), USA

Special Session on Environmental and Geo-spatial Data Analytics (EnGeoData)

Mathieu RocheMaguelonne Teisseire
Cirad, TETIS, FranceIrstea, TETIS, France

Aims and Scope:
Environmental and more generally geo-spatial information is now provided by crowdsourcing but also by public administrations in the context of the open data policies. Analyses of such data are still challenging. Firstly because of their heterogeneity (structural, semantic, spatial and temporal), and secondly because of the difficulty in choosing the "best" knowledge discovery process to apply, according to the needs of the experts in the field. This special session aims at discussing and assessing some of these strategies covering all or part of the issues mentioned above, from a theoretical or experimental point of view.

Topics of interest include:
- Pre and Post Data processing
- Data Quality, Result Evaluation
- Data Mining or Data Warehousing Applications
- Text-Mining
- Visual Analytics
- KDD real use-cases dedicated to environmental and geo-spatial Data

Special Session: Exploratory Computing (EC)

Paolo PaoliniGabriella PasiNicoletta Di Blas
Politecnico di Milano, Italy Università di Milano Bicocca, Italy Politecnico di Milano , Italy

Aims and Scope
The aim of this Special Session is to bring together innovative and original research approaches at the crossroads of several different disciplines: Data Analysis, Exploratory Search, Data Exploration, Information Retrieval, Design and Human-Computer Interaction. The rationale behind the Exploratory Computing approach is to provide users with a rich data/information exploratory experience that encompasses a wide range of different operations including data analysis, exact and approximate query-answering, generation of quick and summarized answers, personalized and context-aware answers, recommendation, data exploration, data visualization etc., synergically combined to provide users with the necessary feedback to progress towards another exploratory step.

“Exploratory Computing” makes reference both to the variegated user scenarios described above and to the powerful computation tools that are needed in order to make the exploration effective.

The special session on Exploratory Computing aims at gathering ground-breaking contributions to pave the way towards a new paradigm for dealing with structurally and semantically complex data.

This is a multi-faceted challenge, which encompasses all the phases of the creation process of an EC system, from computational issues to user experience design.

Topics Of Interest
Topics of interest includes (but are not limited to):

  • Information and data exploration

  • Rich data set management

  • Data Analytics

  • Aggregated Search

  • Data Visualization

  • Exploratory interfaces (HCI)

Program Committee (to be completed)

Special Session on Emotion and Sentiment in Intelligent Systems and Big Social Data Analysis (SentISData)


Cristina BoscoErik CambriaPaolo Rosso
University of Torino, Italy Nanyang Technological University, Singapore Technical University of Valencia, Spain

Viviana PattiRossana Damiano
University of Torino, Italy University of Torino, Italy

Aims and Scope:
The rise of social media and the availability of big social data represent a challenge and a push forward for research on emotion and sentiment, which can meaningfully contribute to the investigation on affective cognitive models and their integration into intelligent systems. Social media are typical contexts for the emergence of subjective and expressive dimensions, but both the huge amount of data available and the relative dilution, within these data, of the meaning to be extracted, have to be carefully taken into account. Moreover, the role of the affective dimension is crucial also for systems interacting with humans in communicating data, where affect can contribute to convey the complex meanings underlying data.

This calls for delving into the evolution of approaches, techniques and tools for modeling and analyzing emotion and sentiment, with the aim of dealing with the affective information conveyed by media that reflect spontaneous, unstructured user responses, and applying big social data analysis within a dynamic corpus of contents, created and enriched by users according to new paradigms of interactions fostering emotional engagement.

Big social data analysis is interdisciplinary and combines areas such as natural language processing, social network analysis, multimedia management, social media analytics, trend discovery, information retrieval, computational linguistics. The goal of this special session is to collect contributions on the development and application of techniques for analysing big social data, with a special focus on sentiment analysis and opinion mining, and on research about paradigms for the integration of emotional states in intelligent systems, to improve systems both for what concerns emotion-awareness and affective human-computer interaction.

Topics of interest include but are not limited to:

  • Emotion and sentiment in social media and big data

  • Subjectivity, sentiment and emotion detection in social media

  • Sentiment-based indexing, search and retrieval in social media

  • Sentiment topic detection & trend discovery

  • Emotion, sentiment and social network analysis

  • Time evolving opinion & sentiment analysis

  • Emotions, sentiment and places

  • Using big social data to measure happiness

  • Emotion models and ontologies of emotions

  • Affect in natural language

  • Emotion-aware intelligent systems

  • Emotions in human-agent interaction and communication

  • Emotions, affect and data visualisation

  • Applications of sentiment and big data analysis on social sciences, e-participation, political forecasting, commerce, tourism, education, healthcare, cultural heritage, etc.

Special Session on Statistical and Mathematical Tools for Data Science (SMTDS)

Marianne ClauselGuillaume BouchardEric Gaussier
IMAG, LIG, FranceXEROX, FranceIMAG, LIG, France

Aims and Scope:

Huge amounts of data are now easily and legally available on the Web. This data is generally heterogeneous and merely structured. Data mining and Machine learning models which have been developed to automatically retrieve, classify or cluster observations on large yet homogeneous data collections have to be rethought. Indeed, many challenging problems, inevitably associated to Big Data, have manifested the needs for tradeoffs between the two conflicting goals of speed and accuracy. This has led to some recent initiatives in both theory and practice from different communities as machine learning, data mining and statsitics. The goal of this special session is to bring together research studies aiming at developing new data mining and machine learning tools to handle new challenges associated to data science.