Title: Understanding Patterns of Awareness -- Towards a Social Media Analytics Experiment for HIV/AIDS and Treatment.

Abstract: Awareness is an estimate of the assertion that a person or a group of people ``know about'' a topic sufficiently well to act upon it. In the case of a communicable disease, it is extremely important for an at-risk population to be aware of the disease, its risk factors, options for its prevention and treatment, and hopefully, to take measures to avoid contracting the disease. Is it, however, possible to estimate the level of awareness of a population toward a disease? Can social media be analyzed to make such an estimation?

this talk, we describe a data acquisition, storage and analysis platform called AWESOME where we investigate the above question in the light of HIV/AIDS. The platform is designed to accept real-time tweets and shred them into an analytical polystore. A suite of cross-data-model conversation analysis strategies is being employed to discover the conversation topics as well as the subpopulation of participants, and how they change over time. The talk with illustrate some invetigative search strategies conducted with AWESOME that will uncover interesting patterns of HIV and PrEP awareness. It will also discuss some open challenges with the problem of awareness understanding and why they are important to improve the quality of awareness estimation.

Bio: Amarnath Gupta is a Research Scientist at the San Diego Supercomputer Center and an Affiliate Faculty of Computer Science and Engineering and at the Halicioğlu Data Science Institute at University of California San Diego. His research interests include large-scale data management, knowledge engineering, graph analytics, information integration and polystore systems for heterogeneous analytics. He is actively involved in interdisciplinary research applying data management research to problems in biomedical science, political science, health informatics and legal applications. Dr. Gupta received a B.Tech. degree in Mechanical Engineering, an M.S. degree in Biomedical Engineering and his Ph.D. (Engineering) in Computer Science.

Title: Frauds and Crimes in Online Social Network: A Review.

Abstract: With the widespread use of computers, communications infrastructure, and the Internet, online social networks (OSN) have gained a huge popularity in recent years. Unfortunately, the very nature and popularity of OSN have brought about its own share of frauds and misuse. Frauds and crimes in OSN refer to activities that result in fear, harassment, loss of money, loss of reputation of a person or an entity, loss of trust in the system or an individual, etc. Due to the complex structure, and information flow in OSN, as well as the relative anonymity of the identity, detection, control and prevention of frauds and crimes in OSN is difficult, time-consuming, error-prone and demands an unusually high level of technical finesse from the investigators. In this talk, we begin with a simple typology of OSN frauds and crimes and then follow up by describing in detail the nature of each fraud / crime and by reviewing some of the state-of-the-art research done so far (mostly in machine learning, data mining, and text mining) to detect them. Where possible, we stress on the scale and impact of these frauds. We identify manipulation of identities and diffusion of misinformation as two important aspects in the modus operandi of most types of OSN frauds and crimes. We identify manipulation of identities and diffusion of misinformation as two important aspects in the modus operandi of most types of OSN frauds and crimes.

Bio: Girish Keshav Palshikar obtained an M.Sc. (Physics) from Indian Institute of Technology, Bombay in 1985 and an M.S. (Computer Science and Engineering) from Indian Institute of Technology, Madras in Jan. 1988. Since 1992, he is working in TCS Research, TRDDC, Pune, India, where he is now a principal scientist and leads the Machine Learning R&D Group. In 2012, he was honoured with the title of TCS Distinguished Scientist. TCS Research is the R&D organization within Tata Consultancy Services Limited - a premier software company in India with ~350,000 employees and the annual revenues of USD16.5 billion in 2015-2016. Girish has ~120 publications in international journals and conferences. He is also a visiting lecturer at the Computer Science Department of University of Pune and Government College of Engineering, Pune (GCOEP). His areas of research include machine learning, data mining, text mining, natural language processing and their applications to various domains, including fraud detection and human resource management. Soft copies of his papers and presentations are available at https://sites.google.com/sites/girishpalshikar.

Title: Investigating the drivers behind spreading of drug abuse contents over Twitter.

Abstract: Prescription drug abuse is a fast-growing menace that is affecting a large section of youths across several societies. Reported casualties of prescription drug abuse are increasing steadily every year. However, tweets sharing positive experiences about drug abuse are also gaining volume rapidly. Although it is not established whether such communications play a direct role in the spread of drug abuse, however, based on models like uses and gratification theory and health communication media choice, it can be argued that such discussions would provide a communication channel that drug abusers can readily use to fulfill their communication needs. Consequently, such discussions would steadily volume up as social advertisements that would tend to glorify drug abuse behavior, aggravating the problem further. Hence it becomes necessary to investigate how social media is playing a role in promoting the drug menace.

In this talk, we initially discuss methods to unravel the underlying social network of the users who engage in the spread of drug abuse contents over Twitter. We subsequently investigate the characteristics of the network and the users participating in these networks to understand the dynamics of the spread of these contents and discover the major players who contribute to such spread. Finally, we discuss ways to study the variation in engagement pattern of the users with respect to different drug names that are being widely abused.

Bio: Joydeep Chandra is an Assistant Professor in the Department of Computer Science and Engineering at Indian Institute of Technology Patna, India. He received his PhD from Indian Institute of Technology, Kharagpur, India in 2012. He was also a research fellow at the Chair of Systems Design at ETH Zurich. His current research interest includes mining social media, modeling of social networks, studying diffusion of information and identifying influentials. The application domains that he works include Journalism, Disaster, Healthcare and Crimes on the Web. More details about him can be found at http://www.iitp.ac.in/~joydeep.

Title: Social Media Analytics for Mental Health: Opportunities and Challenges

Abstract: Mental health problems are getting increasingly recognized as causes of high costs to societies and organizations worldwide with impact ranging into millions of years of productivity loss among various age groups. Mental health problems often exhibit as subtle changes in behavior (including social interactions), therefore, their impact often goes unrecognized – for example – mild depression leading to productivity loss for employed workforce. As mental health issues may remain unnoticed for long, their early detection has potential to play critical role in preliminary intervention and management. Can technology come to help?

In this talk, we will critically review state-of-the-art in Social Media Analytics (SMA) based solutions for addressing mental health challenges. Talk will highlight distinguishing features of SMA based solutions in contrast to other behavioral intervention technologies, present challenges in designing truly effective solutions, and potential approaches to overcome those challenges.

Bio: Janardan Misra is Technology Research Sr. Principal at Accenture Labs, Bangalore with active interest in basic and applied research in areas of Text Analytics, Machine Learning, Data Engineering, and Complex Systems with focus on various business and social-good challenges including mental health. His research contributions appear as published papers in multiple venues and as patents across multiple geographies. He regularly volunteers as a reviewer for various journals including IEEE TNNLS, Elsevier Neurocomputing, IEEE TETCI, ACM TOPC etc. For more information on research please look at https://sites.google.com/site/janardanmisrahomepage/ and for profile details at https://www.linkedin.com/in/janardan/.