Dr. Haggai Roitman
IBM Research - Haifa
Harnessing Social-Sensors – Challenges and Applications
Every moment, anywhere in the world, people are using various social-media services. By doing so, users are (unconsciously) acting as social sensors, whose "sensor readings" are their manually generated data and online interactions. People interact with online content and contribute massive amounts of user-generated content by annotating content, documenting their daily life experiences, reporting on their physical locations and social interactions with others, expressing opinions and providing diverse observations on both the physical world (sights, sounds, smells, feelings, etc.) and the online world (news, music, events, etc.).
Such massive amounts of ubiquitous social sensors, if wisely utilized, can provide new forms of valuable information that are currently not available by any traditional data collection methods including real physical sensors, and can be used to enhance decision making processes.
Effective mining, analyzing, fusing, and exploiting information sourced from social sensors is still an open and exciting challenge. Many factors contribute to the complexity of the problem, including the possible real-time element of the data processing; the heterogeneity of the sources and the ubiquitous and noisy nature of the human-sensor generated information, which can be written in an informal style, duplicated, incomplete or even incorrect.
In this talk I will discuss the main challenges of social-sensing. I will then review several related works that we conducted in IBM Research in Haifa which utilize social-sensors and their user-generated data for various tasks such as enhancing text mining tasks, improving search, event discovery in smart cities and marketing.
Haggai Roitman is a senior researcher, technical leader and master inventor at IBM Research - Haifa (HRL), a member of the information retrieval research group. His research is focused on modelling, analyzing and predicting all aspects of users and consumers behaviour. His research challenges include large scale data mining of diverse "user signals" (e.g., user generated content, online interactions, locations, etc), discovery of various behavioural patterns and analysis of social ties and structures, and the monetization of extracted user models in various domains such as telco, retail, CRM, consumer products, marketing, healthcare, etc.