Out of the Echo Chamber: Detecting Countering Debate Speeches

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7073–7086 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 7073 Out of the Echo Chamber: Detecting Countering Debate Speeches Matan Orbach, Yonatan Bilu, Assaf Toledo, Dan Lahav, Michal Jacovi, Ranit Aharonov and Noam Slonim IBM Research {matano,yonatanb,michal.jacovi,noams}@il.ibm.com {assaf.toledo,dan.lahav, ranit.aharonov}@ibm.com Abstract An educated and informed consumption of media content has become a challenge in mod- ern times. With the shift from traditional news outlets to social media and similar venues, a major concern is that readers are becoming en- capsulated in ”echo chambers” and may fall prey to fake news and disinformation, lacking easy access to dissenting views. We suggest a novel task aiming to alleviate some of these concerns – that of detecting articles that most effectively counter the arguments – and not just the stance – made in a given text. We study this problem in the context of debate speeches. Given such a speech, we aim to identify, from among a set of speeches on the same topic and with an opposing stance, the ones that di- rectly counter it. We provide a large dataset of 3685 such speeches (in English), annotated for this relation, which hopefully would be of gen- eral interest to the NLP community. We ex- plore several algorithms addressing this task, and while some are successful, all fall short of expert human performance, suggesting room for further research. All data collected during this work is freely available for research1. 1 Introduction Recently, a publication on Quantum Computing described a quantum computer swiftly performing a task that arguably would require 10,000 years to be solved by a classical computer (Arute et al., 2019). A non-expert reader is likely to consider this claim as a hard-proven fact, especially due to the credibility of the venue in which this pub- lication appeared. Shortly afterwards, a contest- ing blog written by other experts in that field2 1https://www.research.ibm.com/ haifa/dept/vst/debating_data.shtml# DebateSpeechAnalysis 2https://www.ibm.com/blogs/research/ 2019/10/on-quantum-supremacy/ argued, among other things, that the aforemen- tioned problem can be simulated on a classical computer, using proper optimizations, in 2.5 days. Clearly, out of potentially many texts questioning the promise of Quantum Computers (e.g. Kalai (2019)), making readers of the former publication aware of that specific blog post, which directly contests the claims argued in that publication, will provide them with a more informed view on the issue. Broadly, argumentative texts, such as articles that support a certain viewpoint, often lack argu- ments contesting that viewpoint. This may be be- cause those contesting arguments are not known to the author of the text, as they might not even have been raised at the time of writing. Alterna- tively, authors may also deliberately ignore certain known arguments, which might undermine their argumentative goal. Regardless of the reason, this issue places readers at a disadvantage. Lacking familiarity with opposing views that specifically challenge a given perspective, may lead to unin- formed decisions or establishing opinions based on partial or biased information. Therefore, there …

Content truncated to 500 words