Deep Ordinal Regression for Pledge Specificity Prediction

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 1729–1740, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 1729 Deep Ordinal Regression for Pledge Specificity Prediction Shivashankar Subramanian Trevor Cohn Timothy Baldwin School of Computing and Information Systems The University of Melbourne shivashankar@student.unimelb.edu.au {t.cohn,tbaldwin}@unimelb.edu.au Abstract Many pledges are made in the course of an election campaign, forming important corpora for political analysis of campaign strategy and governmental accountability. At present, there are no publicly available annotated datasets of pledges, and most political analyses rely on manual analysis. In this paper we col- late a novel dataset of manifestos from eleven Australian federal election cycles, with over 12,000 sentences annotated with specificity (e.g., rhetorical vs. detailed pledge) on a fine- grained scale. We propose deep ordinal regres- sion approaches for specificity prediction, un- der both supervised and semi-supervised set- tings, and provide empirical results demon- strating the effectiveness of the proposed tech- niques over several baseline approaches. We analyze the utility of pledge specificity model- ing across a spectrum of policy issues in per- forming ideology prediction, and further pro- vide qualitative analysis in terms of captur- ing party-specific issue salience across elec- tion cycles. 1 Introduction Election manifestos play a critical role in struc- turing political campaigns. Campaign communi- cation can influence a party’s reputation, credibil- ity, and competence, which are primary factors in voter decision making (Fernandez-Vazquez, 2014). Among the various campaign-related func- tions fulfilled by manifestos (Eder et al., 2017), perhaps the most important is the contract they represent between parties and voters in terms of pledges and prioritisation of political issues (Royed et al., 2019). Political scientists have long studied how specific pledges translate into govern- ment programs and actual policy (Royed, 1996; Thomson, 2001; Naurin, 2011; Schermann and Ennser-Jedenastik, 2014). Other work relates spe- cific pledges to the issue clarity of a political party through selective emphasis, which complements salience theory (Robertson et al., 1976; Budge and Farlie, 1983; Praprotnik, 2017). For example: we commit ... 30 per cent tax rebate or cash benefit on the cost of private health insurance premiums conveys the party’s support for private health in- surance, and is more verifiable than: we will improve the health system. Issue clarity has also been shown to be influenced by a party’s ideological position and its role in government (Praprotnik, 2017). Although pledge specificity prediction is an im- portant task for the analysis of party position, pri- orities, and post-election policy framing, to date, almost all research has relied on manual analysis. Subramanian et al. (2019) is a recent exception to this, in performing speech act classification over political campaign text, where the class schema in- cludes the distinction between specific and vague pledges (binary specificity class). In this paper, we perform fine-grained pledge specificity prediction, which is more expressive than binary levels (Li et al., 2016; Gao et al., 2019). We use a class schema proposed …

Content truncated to 500 words