Parsing argued opinion structure in Twitter content
- PDF / 1,109,054 Bytes
- 27 Pages / 439.642 x 666.49 pts Page_size
- 115 Downloads / 207 Views
Parsing argued opinion structure in Twitter content Asma Ouertatani1 · Ghada Gasmi2 · Chiraz Latiri3 Received: 3 April 2020 / Revised: 7 September 2020 / Accepted: 8 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, we address the opinion argumentation mining issue from Twitter data with the objective of further analyzing Twitter users’ preferences and motivations. After introducing the argued opinion definition and its different elements, we propose an argued opinion mining system called T OMAS where we present an end-to-end approach to parse the structure of the argued opinion in order to identify its elements. Our suggested system consists of four consecutive sub-tasks, namely: (1) opinion-topic detection, (2) argumentative opinions identification, (3) argument components detection, and (4) argumentative relation recognition. The proposed system optimizes the argued opinion structure using different classification models. The experimental study is conducted on the MC2 Lab CLEF2017 tweets corpus while considering various comparative baselines. We highlight that our system significantly outperforms the majority baselines and significantly outperforms challenging existing approaches. Keywords Argued opinion · Opinion mining · Argumentation · Twitter messages
1 Introduction and motivations 1.1 Motivations With the advance of Web 2.0, we have recognized the value of opinionated content scattering around social media. In particular, microblogging has become a very popular
Asma Ouertatani
[email protected] Ghada Gasmi [email protected] Chiraz Latiri [email protected] 1
ENSI-STICODE, University of Manouba, Tunis, Tunisia
2
LISI research Laboratory, INSAT, University of Carthage, Tunis, Tunisia
3
LIPAH research Laboratory, FST, Tunis EL Manar University, Tunis, Tunisia
Journal of Intelligent Information Systems
communication tool among Internet users, being Twitter by far the most widespread microblogging platform. It has grown into a technology which allows assessing the public opinion and sentiment analysis as a chance for studying the convergence of points of view and claims in dispute. The goal of opinion mining is to understand what other people think about something or someone? which is always an important piece of information for most of us during the decision-making process (Pang and Lee 2008). Whereas, the aim of argumentation mining is to understand why, which implies looking for arguments and reasons rather than just for opinions and sentiments. Obviously, argumentation mining shares a natural link with opinion mining. Indeed, in many cases, opinions by themselves do not provide arguments, as they do not necessarily imply giving reasons or evidence for accepting a particular conclusion. However, from a meta-level perspective, decision makers devote much effort in analyzing the reasons underlying complex collections of opinions, as they indicate the willingness of people to accept or reject some particular issues. Indeed, i
Data Loading...
