Stance Detection on Social Media: State of the Art and Trends

Abstract

Stance detection on social media is an emerging opinion mining paradigm for various social and political applications where sentiment analysis might be sub-optimal. This paper surveys the work on stance detection and situates its usage within current opinion mining techniques in social media. An exhaustive review of stance detection techniques on social media is presented, including the task definition, the different types of targets in stance detection, the features set used, and the various machine learning approaches applied. The survey reports the state-of-the-art results on the existing benchmark datasets on stance detection, and discusses the most effective approaches.In addition, this study explores the emerging trends and the different applications of stance detection on social media. The study concludes by providing discussion of the gaps in the current existing research and highlighting the possible future directions for stance detection on social media.

Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation

“…Stance detection task aims to identify the stance toward a specific target (Mohammad et al, 2016b;Küçük and Can, 2020;AlDayel and Magdy, 2020). The target is usually a political figure Darwish et al, 2017;Grimminger and Klinger, 2021;Li and Caragea, 2021a;Li et al, 2021), a controversial topic such as marijuana legalization (Hasan and Ng, 2014;Mohammad et al, 2016a;Xu et al, 2016;Taulé et al, 2017;Swami et al, 2018;Stab et al, 2018;Zotova et al, 2020;Conforti et al, 2020a;Lai et al, 2020;Vamvas and Sennrich, 2020;Conforti et al, 2020b;Miao et al, 2020;Glandt et al, 2021) or a claim that could be a rumor's post (Qazvinian et al, 2011;Derczynski et al, 2015;Ferreira and Vlachos, 2016;Bar-Haim et al, 2017;Rao and Pomerleau, 2017;Derczynski et al, 2017;Gorrell et al, 2019).…”

“…These opinions can provide valuable insights into important events, e.g., legalization of abortion. The goal of stance detection is to determine whether the author of a text is in favor of, against or neutral toward a specific target (Mohammad et al, 2016b;Küçük and Can, 2020;AlDayel and Magdy, 2020). For example, for the tweet in 1 https://github.com/chuchun8/ MDL-Stance-Distillation…”