SENTAL: UKP

SENTAL

Sentiment Analysis for User Generated Discourse in eLearning 2.0

Motivation

One prominent feature of eLearning 2.0 is collaboration. Members interact, learn
and share their opinions by creating mass amount of discourse through wikis, blogs and
forums. However, this growing amount of user generated discourse places considerable
burdens on learners as well as instructors who wish to track learners' opinions and views
on diverse topics or search for content containing opinions.

Goals

Enabling subjectivity and sentiment analysis for generating feedback from user generated discourse and for supporting information search in eLearning 2.0:

investigate knowledge- and corpus-based methods for subjectivity and sentiment analysis
determine the semantic orientation and strength of the opinions
identify the targets of the opinions
identify the holders of the opinions

System Architecture

Project Publications

Displaying results 1 to 2 out of 2

Sentence and Expression Level Annotation of Opinions in User-Generated Discourse

Cigdem Toprak and Niklas Jakob and Iryna Gurevych
In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010), p. 575 -- 584, Association for Computational Linguistics, July 2010.

Document Level Subjectivity Classification Experiments in DEFT'09 Challenge

Cigdem Toprak and Iryna Gurevych
In: Proceedings of the DEFT'09 Text Mining Challenge, p. 89-97, June 2009.