BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:BlogLearn: A Framework for Analytics over Corporate Blogs - Sudars
 han Murthy (Wipro Technologies)
DTSTART:20100301T110000Z
DTEND:20100301T120000Z
UID:TALK23545@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Corporate blogs contain rich information such as organizationa
 l structure and sentiment\,\nbut much of this information tends to be impl
 icit. Thus\, the first step in analyzing\nthese blogs is to create data mo
 dels and techniques that enable unified access to the explicit\nand implic
 it information.\nBlogLearn is an analytics framework we have developed to 
 aid analytics over corporate\nblogs. It exposes blog data both in native f
 ormat (posts\, authors\, readers\, and so on) and as a\ngraph of co-occurr
 ing concepts. It includes a means to identify and classify concepts\, and 
 it\nlets analysts build a concept hierarchy using both is-a and is-in rela
 tionships. It allows concepts\nto be typed\, but it makes no distinction b
 etween a type and an instance.\nWe have used BlogLearn to characterize and
  analyze real corporate blogs. For example\, we\nhave used BlogLearn to in
 fer which authors and readers influence the blogosphere\, and we\nhave use
 d it to discover the conditional probability of concept co-occurrence. We 
 are also\nusing BlogLearn (on itself\, via co-occurrence graphs) to automa
 te the placement of a concept\nin a hierarchy.\nOur experience with BlogLe
 arn has convinced us that co-occurrence graphs are a useful tool\nto analy
 ze corporate blogs. In future\, we plan to use the graphs to identify cent
 ral concepts\n(for users) and central users (for concepts). We also plan t
 o use conditional probabilities to\nexamine biases that might be inherent 
 in corporate blogs.\nBlogLearn is a result of ongoing joint research by Ap
 plied Research at Wipro Technologies\nand the International Institute of I
 nformation Technology\, Bangalore.\n\nBio: Dr. Sudarshan Murthy directs th
 e Applied Research group in Wipro\nTechnologies\, headquartered in Bangalo
 re\, India. He has a PhD (CS) from the Portland State\nUniversity and a Ma
 sters (CS) from the erstwhile Oregon Graduate Institute. Before joining\ng
 raduate school\, Dr. Murthy founded and operated a software process-engine
 ering business\,\nand before that developed international-trade-finance ap
 plications for leading banks. He has\nalso taught undergraduate and gradua
 te classes in software engineering and data management.\nDr. Murthy is als
 o a law junkie.
LOCATION:FW11\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR