Welcome to the website for Lexicoder, Java-based, multi-platform software for automated content analysis of text. The newest version of Lexicoder (v3.0), released in August 2015, was developed by Mark Daku, Stuart Soroka and Lori Young (all initially at McGill University, and now at McGill, Michigan and Penn respectively).
The current version of the software is freely available - for academic use only - here. Additions and revisions will also be released here as they become available. In addition, the Lexicoder Sentiment Dictionary, a dictionary designed to capture the sentiment of political texts, is available here formatted for Lexicoder and also adaptable to other content-analytic software. Work on Topic Dictionaries, based on the Policy Agendas coding scheme, is also underway. All dictionaries are available on the Download page, alongside other supporting files, software and link from others.
In addition to Lexicoder software and dictionaries, this website includes links to research based on data generated in Lexicoder, and links to other resources for automated content analysis.
Funding for the initial version of Lexicoder was provided by the McGill Institute for the Study of Canada, the McGill-Max Bell Foundation, the Donner Canadian Foundation, and the Fonds québécois de recherche sur la société et la culture.
If you downloaded Lexicoder before 30th August 2015, then there's been an update! Lexicoder 3.0 is now available from the Download page.
This newest version of Lexicoder is used in a recent conference paper exploring policy information in media content. Also see this recent paper, focused on the development of multilingual sentiment dictionaries for the analysis of legislative speech. Relatedly, an ongoing effort to build relaible, mutli-lingual topic dictionaries is discussed in this paper by Quinn Albaugh et al.
The most recent paper on sentiment in economic news, by Stuart Soroka, Dominic Stecula and Christopher Wlezien, is out in the American Journal of Political Science. Read it here.