Critical Digital Humanities by James E. Dobson

Critical Digital Humanities by James E. Dobson

Author:James E. Dobson
Language: eng
Format: epub
Publisher: University of Illinois Press
Published: 2019-03-14T16:00:00+00:00


Mining Sentiment

Following the rather sudden availability of large-scale and rich digital corpora through end-user- or consumer-generated activity on social media and other locations offering free-form commentary in the early years of the twenty-first century, computer and data scientists began to quickly develop methods that could analyze and categorize this otherwise disordered flow of linguistic content. Working with some existing procedures, tools, and data from the field of natural language processing, an interdisciplinary field involving computational linguists, sociologists, and computer scientists, researchers began to mine new digital repositories and social media for a particular type of textual content that they refer to as sentiment. Knowing what, for example, consumers think about a particular product, especially when they imagine that they have some agency in posting their own opinions rather than responding to a survey, has an incredibly large value to marketers and business executives. When taken in the “big data” aggregate, their thoughts or opinions might offer some average sense of what people think about a consumable good or aesthetic object and maybe even offer some nuance about the attributes or aspects of this object.

Sentiment analysis, as used widely within various computational fields, including the digital humanities, has an empirical and deeply ahistorical understanding of sentiment and sentimentality and yet introduces assumptions from the present into the understanding of what constitutes sentiment and feeling. (See figure 3.1.) This paradox emerges through the creation and use of dictionaries and lists that score, rank, and categorize affective language. These dictionaries alter the horizon of interpretation and are a prime example of what I have been calling text-external referential systems.



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.