* News


Towards a Knowledge-Based Web Surveillance Framework

Muhammad Abulaish
Associate Professor, Center of Excellence in Information Assurance, King Saud University, Riyadh, KSA

April 15, 2011
Fischbach Room, Folsom Library- 11:00 a.m. to 12:00 p.m.


Due to easy accessibility and availability of Internet, non-social elements are continuously utilizing it as a cost-effective infrastructure for disseminating information across the globe. Consequently, it is becoming a challenging task for intelligence agencies to track movement and activities of suspects around the globe. Since tracking of a single suspect can generate a large amount of semantic data, important details can be lost in a large volume of text resulting into an information overload problem. Moreover, due to huge size and dynamic nature of the WWW, a constant manual monitoring is not a feasible task and automated Web surveillance using data mining techniques are indispensable for efficiently securing the Web against its misuse. Primarily focusing on extraction of implicit and novel patterns (knowledge) from huge databases (structured data), data mining techniques have also proven to be very effective for analyzing unstructured (text documents) and semi-structured (Web documents) data. Consequently, various research areas including text mining, web mining, and social network analysis have emerged in recent past. In the context of Web surveillance, data mining can be a potential mean to identify suspects and their activities through analyzing Web data and social networks evolved from communication networks including e-mails, enterprise portals, or social networking sites like Facebook, Twitter, etc. Web surveillance involves various aspects of analyzing different metrics, features and processes in Web and social network data which include web-content mining, web- usage mining, community detection, link prediction, position/role analysis, information diffusion, and sentiment analysis. In this talk, we propose the design of a unified knowledge-based Web surveillance framework that combines information retrieval, natural language processing and data mining techniques to identify criminals and their networks on the Web. The proposed framework would provide necessary knowledge for the intelligence agencies to identify individuals who possibly can spread criminal ideologies, criminal profiling, criminal network analysis, and visualization of criminal's activities, linkages and relationships.


Muhammad Abulaish is on leave from Jamia Millia Islamia (A Central University), New Delhi, India and working as an Associate Professor at the Center of Excellence in Information Assurance (CoEIA), King Saud University, Riyadh, KSA. At the center, he is leading the Internet Surveillance and Forensics research team. Abulaish received the Master degree in Computer Science and Applications from MNNIT India. Later, he received Ph.D. degree in Computer Science from Indian Institute of Technology (IIT) Delhi, India. Abulaish has also qualified the National Eligibility Test (NET) in Computer Science and Applications conducted by University Grants Commission (UGC) India. He has more than 12 years Computer Science teaching experience at undergraduate and postgraduate levels. He is a senior member of the Computer Society of India (CSI). He is also a member of IEEE and its Computer Society, ACM, ACM-SIGKDD, ISTE, IETE, and ISCA. Abulaish's current research interests span over the areas of Data Mining, Text Mining, Social Network Analysis, Information Retrieval, Web Intelligence, and Natural Language Processing (NLP). Abulaish has published one monograph entitled "Ontology Engineering for Imprecise Knowledge management", and over 30 research articles in Journals, Books and Conference Proceedings. He is a program committee member of several International Conferences/ Workshops. He is also an editorial board member and reviewer for various reputed journals in his field.

Hosted by: Dr. Mohammed Zaki (x6340)

Last updated: March 28, 2011