MPI-INF Logo
Campus Event Calendar

Event Entry

What and Who

Exploiting Social Network Structure for Person-to-Person Sentiment Analysis

Robert West
Stanford University
SWS Colloquium

Bob obtained a Diplom degree in computer science from the Technical
University of Munich in his native Germany in 2007 and a Master's
degree in computer science from McGill University in 2010. He is
currently a fifth-year Ph.D. candidate in the InfoLab at Stanford
University, advised by Jure Leskovec, where he has been working at the
intersection of data mining, machine learning, and natural language
processing to convert raw log data into meaningful insights on a
number of human behaviors, ranging from navigation in complex networks
to Wikipedia editing to food intake.
AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI  
Expert Audience
English

Date, Time and Location

Wednesday, 26 November 2014
11:00
60 Minutes
E1 5
029
Saarbrücken

Abstract


Person-to-person evaluations are prevalent in all kinds of discourse
and important for establishing reputations, building social bonds, and
shaping public opinion. Such evaluations can be analyzed separately
using signed social networks and textual sentiment analysis, but this
misses the rich interactions between language and social context. To
capture such interactions, we develop a model that predicts individual
A's opinion of individual B by synthesizing information from the
signed social network in which A and B are embedded with sentiment
analysis of the evaluative texts relating A to B. We prove that this
problem is NP-hard but can be relaxed to an efficiently solvable
hinge-loss Markov random field, and we show that this implementation
outperforms text-only and network-only versions in two very different
datasets involving community-level decision-making: the Convote U.S.
Congressional speech corpus and the Wikipedia Requests for Adminship
corpus.
(Joint work with Hristo Paskov, Jure Leskovec, and Christopher Potts)

Time permitting, I will also briefly discuss the "From Cookies to
Cooks" project, where we leverage search-engine query logs to gain
insights into what foods people consume when and where.
(Joint work with Ryen White and Eric Horvitz)

Contact

Brigitta Hansen
0681 93039102
--email hidden

Video Broadcast

Yes
Kaiserslautern
G26
112
passcode not visible
logged in users only

Brigitta Hansen, 11/25/2014 09:25
Brigitta Hansen, 11/24/2014 13:15 -- Created document.