Summarizing Dialogic Arguments from Social Media

TL;DR

This paper develops models to generate concise summaries of online social media dialogues, focusing on identifying key arguments to better understand public opinions on controversial topics.

Contribution

It introduces a new dataset of human-written summaries for social media dialogues and evaluates models that identify important dialogue segments for summarization.

Findings

Achieved up to 0.74 F-measure in argument identification for gun control.

Demonstrated the effectiveness of linguistic and Word2vec features with machine learning models.

Provided insights into summarizing argumentative social media content.

Abstract

Online argumentative dialog is a rich source of information on popular beliefs and opinions that could be useful to companies as well as governmental or public policy agencies. Compact, easy to read, summaries of these dialogues would thus be highly valuable. A priori, it is not even clear what form such a summary should take. Previous work on summarization has primarily focused on summarizing written texts, where the notion of an abstract of the text is well defined. We collect gold standard training data consisting of five human summaries for each of 161 dialogues on the topics of Gay Marriage, Gun Control and Abortion. We present several different computational models aimed at identifying segments of the dialogues whose content should be used for the summary, using linguistic features and Word2vec features with both SVMs and Bidirectional LSTMs. We show that we can identify the most important arguments by using the dialog context with a best F-measure of 0.74 for gun control, 0.71 for gay marriage, and 0.67 for abortion.