Fermi at SemEval-2019 Task 4: The sarah-jane-smith Hyperpartisan News Detector

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 954–956 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 954 Fermi at SemEval-2019 Task 4: The sarah-jane-smith Hyperpartisan News Detector Nikhil Chakravartula1,3 Vijayasaradhi Indurthi1,2, Bakhtiyar Syed2, 1 Teradata, 2 IIIT Hyderabad 1{nikhil.chakravartula,vijayasaradhi.indurthi}@teradata.com 2{vijaya.saradhi, syed.b}@research.iiit.ac.in 3{nikhil.chakravartula}@gmail.com Abstract This paper describes our system (Fermi) for Task 4: Hyper-partisan News detection of SemEval-2019. We use simple text classifi- cation algorithms by transforming the input features to a reduced feature set. We aim to find the right number of features useful for efficient classification and explore multiple training models to evaluate the performance of these text classification algorithms. Our team - Fermi’s model achieved an accuracy of 59.10% and an F1 score of 69.5% on the offi- cial test data set. In this paper, we provide a detailed description of the approach as well as the results obtained in the task. 1 Introduction Hyper-partisan refers to a person or a group’s ten- dency to be extremely partisan or biased towards a person or a group and specifically towards a po- litical person or a political party. With the tremen- dous increase in citizen-based journalism, where anyone can create a website and post his (biased) views, there is a new phenomenon called fake news and it’s potential role in affecting the elec- tion results, and has the ability to modify and im- pact the public’s perception towards various peo- ple, companies and political parties. These kind of ’news’ are usually one-sided, inflammatory, emo- tional and mostly woven around untruths. Com- bined with the proliferation of social media plat- forms, these ’fake news’ signals get amplified and may potentially mask the signal of the real news. The fake news phenomenon hype has caused ir- reparable loss to many politicians, companies and in some cases involved the death of fellow citizens. While Social media platforms can be used for constructive ideas, a small group of people can propagate their notions including hatred or affin- ity towards or against an individual, or a group or a race to the entire world in a few seconds. This necessitates the need to come up with computa- tional methods to identify hyper-partisan news in user generated content. Using computational methods to identify hyper- partisan news has been gaining attention in recent years as evidenced in (Potthast et al., 2018). 2 Related Work In this section, we briefly describe other work in this area. Hyper-partisan news detection is a new area and to the best of the knowledge of the authors, not much work has been done in this area. However, a close and related task is that of fake news de- tection. (P´erez-Rosas et al., 2017) use linguis- tic features to distinguish between fake and legiti- mate news content. (Wang, 2017) collect a decade long manually labelled sor statements in various context from a political fact checking website and create fake news classifiers using surface level lin- guistic patterns. (Tschiatschek et al., 2018) lever- age crowd signals …

Content truncated to 500 words