Policy-focused Stance Detection in Parliamentary Debate Speeches

Policy-focused Stance Detection in Parliamentary Debate Speeches Gavin Abercrombie, Department of Computer Science, University of Manchester gavin.abercrombie@manchester.ac.uk Riza Batista-Navarro, Department of Computer Science, University of Manchester riza.batista@manchester.ac.uk Abstract Legislative debate transcripts provide citizens with information about the activities of their elected representatives, but are difficult for people to process. We propose the task of policy-focused stance detection, in which both the policy proposals under debate and the position of the speakers towards those proposals are identified. We adapt a previously existing dataset to include manual annotations of policy preferences, an established schema from political science. We evaluate a range of approaches to the automatic classification of policy preferences and speech sentiment polarity, including transformer-based text representations and a multi-task learning paradigm. We find that it is possible to identify the policies under discussion using features derived from the speeches, and that incorporating motion-dependent debate modelling, previously used to classify speech sentiment, also improves performance in the classification of policy preferences. The proposed use of contextual embeddings and a multi-task learning paradigm do not perform as well as simpler approaches. We analyse the output of the best performing system, finding that discriminating features for the task are highly domain-specific, and that speeches that address policy preferences proposed by members of the same party can be among the most difficult to predict. 1 Introduction Transcripts of legislative debates provide access to in- formation concerning the policies that are publicly sup- ported or opposed by politicians. They are of interest to political scientists, the media, the politicians them- selves, and citizens who wish to monitor the activities of their representatives. However, such documents are complex and diffi- cult for people to process. Transcripts of debates in the United Kingdom (UK) Parliament are so hard for ordi- nary people to make sense of that parliamentary mon- itoring website www.theyworkforyou.com publishes manually annotated versions of the transcripts. These include crowd-sourced explanations of the debated pro- posals, as well as policy-focused aggregations of the voting records of parliamentarians. The large quantity and esoteric nature of the data in the parliamentary record (known as Hansard) motivates the need for au- tomatic analysis of its contents. Previous work in the domain of legislative debate transcripts has focused on either (a) sentiment polarity classification (Bhavan et al., 2019; Burfoot et al., 2011; Thomas et al., 2006), or (b) policy identification (Aber- crombie and Batista-Navarro, 2018b; Abercrombie et al., 2019) in isolation. As far as we are aware, these two tasks have not previously been combined in this do- main, despite the fact that: (1) the information yielded is complementary, and perhaps even necessary, for practical use (i.e., without analysis of debated policies, the target of sentiment in the speeches is unknown); and (2) these two tasks rely on features derived from shared information, which could assist with the learn- ing of parameters for both tasks in a multi-task learning setting. Borrowing the concept of policy preferences from political science, we compare approaches to automat- ically determining the policy preference …

Content truncated to 500 words