The language used in political discourse varies depending on the worldview of the speaker, and we describe specific instances of politically charged phrases as political frames. A frame is a group of words that appears consistently across political corpora, and is applied to evoke particular emotions or opinions regarding an issue. Such frames get used in all language, whether it is intentional or not. We propose a system that can automatically pull out frames from a corpus using statistical and linguistic analysis. The result of this system is a tool that ingests large amounts of texts and constructs frame matrices — an organizational structure to categorize and document political frames. Overall, the main contribution is in demonstrating the value of such a system and outlining the means through which it can be done.
Title
Underpinnings of Political Leaning: Using Collocation Extraction and Semantic Analysis to Categorize Ideological Frames
Published
2019-05-20
Full Collection Name
Electrical Engineering & Computer Sciences Technical Reports
Other Identifiers
EECS-2019-89
Type
Text
Extent
46 p
Archive
The Engineering Library
Usage Statement
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).
