BlogLearn: A Framework for Analytics over Corporate Blogs

Add to your list(s) Download to your calendar using vCal

• Sudarshan Murthy (Wipro Technologies)
• Monday 01 March 2010, 11:00-12:00
• FW11, Computer Laboratory, William Gates Builiding.

If you have a question about this talk, please contact Eiko Yoneki.

Corporate blogs contain rich information such as organizational structure and sentiment, but much of this information tends to be implicit. Thus, the first step in analyzing these blogs is to create data models and techniques that enable unified access to the explicit and implicit information. BlogLearn is an analytics framework we have developed to aid analytics over corporate blogs. It exposes blog data both in native format (posts, authors, readers, and so on) and as a graph of co-occurring concepts. It includes a means to identify and classify concepts, and it lets analysts build a concept hierarchy using both is-a and is-in relationships. It allows concepts to be typed, but it makes no distinction between a type and an instance. We have used BlogLearn to characterize and analyze real corporate blogs. For example, we have used BlogLearn to infer which authors and readers influence the blogosphere, and we have used it to discover the conditional probability of concept co-occurrence. We are also using BlogLearn (on itself, via co-occurrence graphs) to automate the placement of a concept in a hierarchy. Our experience with BlogLearn has convinced us that co-occurrence graphs are a useful tool to analyze corporate blogs. In future, we plan to use the graphs to identify central concepts (for users) and central users (for concepts). We also plan to use conditional probabilities to examine biases that might be inherent in corporate blogs. BlogLearn is a result of ongoing joint research by Applied Research at Wipro Technologies and the International Institute of Information Technology, Bangalore.

Bio: Dr. Sudarshan Murthy directs the Applied Research group in Wipro Technologies, headquartered in Bangalore, India. He has a PhD (CS) from the Portland State University and a Masters (CS) from the erstwhile Oregon Graduate Institute. Before joining graduate school, Dr. Murthy founded and operated a software process-engineering business, and before that developed international-trade-finance applications for leading banks. He has also taught undergraduate and graduate classes in software engineering and data management. Dr. Murthy is also a law junkie.

This talk is part of the Computer Laboratory Systems Research Group Seminar series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• CL's SRG seminar
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Computer Laboratory Systems Research Group Seminar
• Department of Computer Science and Technology talks and seminars
• FW11, Computer Laboratory, William Gates Builiding
• Interested Talks
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.