Analyzing Discourse Communities with Distributional Semantic Models
|Title:||Analyzing Discourse Communities with Distributional Semantic Models||Authors:||Brigadir, Igor
|Permanent link:||http://hdl.handle.net/10197/6613||Date:||1-Jul-2015||Online since:||2015-06-17T11:32:49Z||Abstract:||This paper presents a new corpus-driven approach applicable to the study of language patterns in social and political contexts, or Critical Discourse Analysis (CDA) using Distributional Semantic Models (DSMs). This approach considers changes in word semantics, both over time and between communities with differing viewpoints. The geometrical spaces constructed by DSMs or 'word spaces' offer an objective, robust exploratory analysis tool for revealing novel patterns and similarities between communities, as well as highlighting when these changes occur. To quantify differences between word spaces built on different time periods and from different communities, we analyze the nearest neighboring words in the DSM, a process we relate to analyzing 'concordance lines'. This makes the approach intuitive and interpretable to practitioners. We demonstrate the usefulness of the approach with two case studies, following groups with opposing political ideologies in the Scottish Independence Referendum, and the US Midterm Elections 2014.||Funding Details:||Science Foundation Ireland||Type of material:||Conference Publication||Publisher:||ACM||Copyright (published version):||2015 ACM||Keywords:||Discourse-historical approach; Critical discourse analysis; Political discourse; Distributional semantics; Scottish independence referendum; US midterm elections; Politics on twitter||DOI:||10.1145/2786451.2786470||Other versions:||http://websci15.org/||Language:||en||Status of Item:||Peer reviewed||Is part of:||WebSci '15 Proceedings of the ACM Web Science Conference||Conference Details:||ACM Web Science 2015 Conference, 28 June - 1 July 2015, Oxford, United Kingdom|
|Appears in Collections:||Computer Science Research Collection|
Insight Research Collection
Show full item record
Page view(s) 20163
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.