Incorporating Label Dependencies in Multilabel Stance Detection

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 6350–6354, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 6350 Incorporating Label Dependencies in Multilabel Stance Detection William Ferreira Lucubo Ltd william@lucubo.com Andreas Vlachos Dept. of Computer Science and Technology University of Cambridge Cambridge, UK av308@cst.cam.ac.uk Abstract Stance detection in social media is a well- studied task in a variety of domains. Nev- ertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an ut- terance can have multiple labels, thus corre- sponding to multilabel classification. We pro- pose a method that explicitly incorporates la- bel dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very com- petitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations. 1 Introduction Stance detection is an established task in the com- putational linguistics community, and is typically concerned with whether an utterance (e.g. a tweet) expresses an attitude (often positive, negative or neutral) against a target such as an entity e.g. a politician (Hasan and Ng, 2013; Mohammad et al., 2016), or another utterance, e.g. a previous tweet in a thread (Zubiaga et al., 2016). Thus stance de- tection is an important task for analyzing discourse in online forums and social media platforms and is a component in assessing the veracity of claims (Kochkina et al., 2018). When the stances are mutually exclusive as in the aforementioned cases, multiclass classification is an appropriate formulation for the task. Often, however, a text may express multiple stances si- multaneously. Such cases need to be formulated as Brexit Blog Corpus (Simaki et al., 2018) Utterance: rivalry between the us and china is inevitable but it needs to be kept within bounds that would preclude the use of military force. Stances: certainty, contrariety, necessity, prediction US Election Twitter Corpus (Sobhani et al., 2019) Utterance: voters mean more than super delegates @sensanders corrupt -> #hillaryclinton spends millions on msm to discourage #americans voting #sanders Stances: Clinton: AGAINST, Sanders: FAVOR Moral Foundations Twitter (Dehghani et al., 2019) Utterance: blatant racism in #colorado, #blacklivesmatter http://fb.me/1ibyxmswm Stances: cheating, harm Figure 1: Examples from each of the datasets. multilabel classification (Sorower, 2010), where an instance can receive multiple, non-mutually exclusive labels. The most commonly used ap- proaches to multiclass classification treat the task by learning models for each label. However, such approaches do not model dependencies between the labels explicitly, i.e. that the presence of one la- bel results in another …

Content truncated to 500 words