Making conversational structure explicit: identification of initiation-response pairs within online discussions

Authors:
Yi-Chia Wang;Carolyn P. Rosé
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Year:
2010

Citing 2
Cited 6

Threading electronic mail: a preliminary study

Information Processing and Management: an International Journal - Special issue: methods and tools for the automatic construction of hypertext
Contextual search and name disambiguation in email using graphs

SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval

Learning online discussion structures by conditional random fields

Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
How can you say such things?!?: recognizing disagreement in informal political argument

LSM '11 Proceedings of the Workshop on Languages in Social Media
Cats rule and dogs drool!: classifying stance in online debate

WASSA '11 Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis
Predicting thread discourse structure over technical web forums

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
That is your evidence?: Classifying stance in online political debate

Decision Support Systems
Stance classification using dialogic properties of persuasion

NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we investigate how to identify initiation-response pairs in asynchronous, multi-threaded, multi-party conversations. We formulate the task of identifying initiation-response pairs as a pairwise ranking problem. A novel variant of Latent Semantic Analysis (LSA) is proposed to overcome a limitation of standard LSA models, namely that uncommon words, which are critical for signaling initiation-response links, tend to be deemphasized as it is the more frequent terms that end up closer to the latent factors selected through singular value decomposition. We present experimental results demonstrating significantly better performance of the novel variant of LSA over standard LSA.