ERTIM@MC2: Diversified Argumentative Tweets Retrieval

TL;DR

This paper describes a method for retrieving diverse and argumentative Tweets about festivals in multiple languages by analyzing argumentation structures and content diversity, with applications in opinion mining.

Contribution

It introduces a novel approach combining linguistic descriptors and clustering to identify diverse, argumentative Tweets in multilingual datasets for opinion argumentation mining.

Findings

Effective detection of argumentative Tweets with high diversity coverage

Successful multilingual processing in English and French

Improved clustering and selection of argumentative content

Abstract

In this paper, we present our participation to CLEF MC2 2018 edition for the task 2 Mining opinion argumentation. It consists in detecting the most argumentative and diverse Tweets about some festivals in English and French from a massive multilingual collection. We measure argumentativity of a Tweet computing the amount of argumentation compounds it contains. We consider argumentation compounds as a combination between opinion expression and its support with facts and a particular structuration. Regarding diversity, we consider the amount of festival aspects covered by Tweets. An initial step filters the original dataset to fit the language and topic requirements of the task. Then, we compute and integrate linguistic descriptors to detect claims and their respective justifications in Tweets. The final step extracts the most diverse arguments by clustering Tweets according to their textual content and selecting the most argumentative ones from each cluster. We conclude the paper describing the different ways we combined the descriptors among the different runs we submitted and discussing their results.