SoMeRis: Social Media and Risk
ASONAM 2015 workshop
supported by the AXA-Polytechnique DASCIS chair

25/08/2015    8:30 - 13:00    Telecom, B551


Organizers


Check also the 2nd SoMeRis workshop, held in conjunction with ICDM'16. Discover other ASONAM 2015 workshops here. Download here the ASONAM 2015 full program.


Find Out More

Call for Papers

The aim of this workshop is to address state-of-the-art techniques in machine learning, graph and text mining to leverage information available in social media to enrich and improve predictive algorithms for risk assessment and management, such as the insurance sector or the online industry. A (non restrictive) list of topics follows:

Risk management

  • Social media for risk assessment in online industry
  • Social media for risk in the insurance sector
  • The nature of risk in the insurance sector

Social media

  • Graph/Text Mining for social media
  • Dynamics of social networks

Privacy

  • Privacy in Social media
  • Fraud detection and prevention
  • Sharing economics, social networks and peer-to-peer insurance

The workshop will host two keynotes by a major insurance company (AXA), and several academic and industrial talks. The objective is to create an interface between academics and practitioners, to exchange and create synergies about challenging problems at the crossing of machine learning on social media and industrial applications that involve risk assessment and management. This topic is particularly relevant and unexplored. The exploitation of such sources of information for risk-based businesses is a relatively recent topic. It requires new developments both on the methodological and technological aspects: from new statistical models that describe accurately the dynamics of social media and information diffusion, to the use of APIs and relevant databases to crawl, structure and exploit data from social media. Needless to stress that the dominant structures in this case are the graphs enriched with the textual content of user interactions and histories.

Key Dates

April 30, 2015 May 17, 2015: Due date for paper submission

June 10, 2015: Notification of paper acceptance to authors

June 25, 2015: Camera-ready deadline for accepted papers

August 25, 2015: Workshop date

ACCEPTED PAPERS

Privacy Tips: Would it be ever possible to empower on-line social network users to control the confidentiality of their data?
Vladimir Estivill-Castro and David F. Nettleton

Finding compact communities in large graphs
Jean Creusefond, Thomas Largillier and Sylvain Peyronnet

Community-Preserving Generalization of Social Networks
Jordi Casas-Roma and François Rousseau

Graph-Based Term Weighting for Text Categorization
Fragkiskos D. Malliaros and Konstantinos Skianis

Multi-layered graph-based model for social engineering vulnerability assessment
Omar Jaafor and Babiga Birregah

TipMe: Personalized advertising and aspect-based opinion mining for users and businesses
Dimitris Proios, Magdalini Eirinaki and Iraklis Varlamis

Feature Extraction and Analysis for Identifying Disruptive Events from Social Media
Nasser Alsaedi and Pete Burnap

Programme Committee

Klaus Berberich, Max Planck Institute for Informatics, Germany

Jordi Casas Roma, Open University of Catalonia, Spain

Manuel Gomez Rodriguez, Max Planck Institute for Software Systems, Germany

Marc Lelarge, École Normale Supérieure, France

Fragkiskos Malliaros, Ecole Polytechnique, France

Kjetil Nørvåg, Norwegian University of Science and Technology, Norway

Claudia Tarantola, University of Pavia, Italy

Iraklis Varlamis, Harokopio University of Athens, Greece

Program

Download here the ASONAM 2015 full program.

8:30 - 9:15
Keynote: GUSDORF Raphael (AXA)

Bio: Raphaël Gusdorf holds a Master’s Degree in Management from NEOMA Reims Business School. He has over 15 years of experience in the Insurance and Banking sector, more specifically in the Risk Management area. He joined AXA in 2010 and worked for 4 years in the Group Risk Management department, in charge of Operational Risk before joining the AXA Research Fund – the Science Philantropy Initiative of the AXA Group – as Head of Selection.

Title: Social Networks and Economics of Data – How do a large financial firm like AXA integrate Social Networks and Big Data capabilities to transform their business processes, from employer’s brand to customer satisfaction.

Abstract: Insurance companies have long ago relied on large sets of sensitive data to feed their actuarial expertise and be able to predict something unpredictible: RISKS. The emergence of the Economics of Data and Social Networks, however, has introduced major changes on the whole value chain of Insurance Companies, impacting not only their technical processes, but also employer’s brand, pricing, information security and confidentiality, marketing and media strategy, customer relationship and, ultimately, TRUST.

9:15 - 9:35
Graph-Based Term Weighting for Text Categorization, Fragkiskos D. Malliaros and Konstantinos Skianis

9:35 - 9:55
Finding compact communities in large graphs, Jean Creusefond, Thomas Largillier and Sylvain Peyronnet

9:55 -10:15
Community-Preserving Generalization of Social Networks, Jordi Casas-Roma and François Rousseau

coffee - break

11:00 - 11:45
Keynote: Françoise Soulié (AXA)

Bio: Françoise Soulié Fogelman has over 40 years’ experience in data mining, social network analysis and big data both in academia and industry. A former graduate from École Normale Supérieure, she holds a PhD from University of Grenoble. She was Professor at the University of Paris 11-Orsay, where she was advisor to 20 PhDs. She then funded a startup (Mimetics) to later join Atos (as head of a data mining – data warehouse group) and Business & Décision (as Partner) where she created and headed the CRM business unit. At KXEN, she has been Vice President Innovation until the company was bought out by SAP. Finally she joined Institut Mines Télécom where she worked for the Big Data platform TeraLab. She is presently Professor with the School of Computer Software at Tianjin University, head of the Data Science team. She has co-authored more than 120 scientific publications and 13 books. She is an expert for the European Commission and ANR.

Title: Social Network Analysis for Fraud Detection and Investigation

Abstract: Social Network Analysis brings a large number of techniques which can be used to analyze fraud, both predicting fraud risk and investigating fraud schemes. I will present the methodology for fraud risk detection and for fraud investigation and will show on two examples what SNA can bring in such applications.

11:45 - 12:05
Privacy Tips: Would it be ever possible to empower on-line social network users to control the confidentiality of their data?, Vladimir Estivill-Castro and David F. Nettleton

12:05 - 12:25
Multi-layered graph-based model for social engineering vulnerability assessment, Omar Jaafor and Babiga Birregah

12:25 - 12:45
TipMe: Personalized advertising and aspect-based opinion mining for users and businesses, Dimitris Proios, Magdalini Eirinaki and Iraklis Varlamis

12:45 - 13:05
Feature Extraction and Analysis for Identifying Disruptive Events from Social Media, Nasser Alsaedi and Pete Burnap

Contact Us

CAPTCHA Image