Doctor of Philosophy (PhD)
Curriculum and Instruction
First Advisor's Name
First Advisor's Committee Title
Second Advisor's Name
Second Advisor's Committee Title
Third Advisor's Name
Third Advisor's Committee Title
Fourth Advisor's Name
Fourth Advisor's Committee Title
Sentiment analysis, dialogic communication theory, Microblog Dialogic Communication, Twitter
Date of Defense
The purpose of the present study is to ascertain if colleges are achieving their ultimate communication goals of maintaining and attracting students through their microblogging activity, which according to Dialogic Loop Theory, is directly correlated to the use of positive and negative sentiment. The study focused on a cross-section of urban and rural community colleges within the United States to identify the sentiment score of their microblogging activity. The study included a content analysis on the Twitter activity of these colleges. A data-mining process was employed to collect a census of the tweets associated with these colleges. Further processing was then applied using data linguistic software that removed all irrelevant text, word abbreviations, emoticons, and other Twitter specific classifiers. The resulting data set was then processed through a Multinomial Naive Bayes Classifier, which refers to a probability of word counts in a text. The classifier was trained using a data source of 1.5 million tweets, called Sentiment140, that qualitatively analyzed the corpus of these tweets, labeling them as positive and negative sentiment. The Multinomial Naive Bayes Classifier distinguished specific wording and phrases from the corpus, comparing the data to a specific database of sentiment word identifiers. The sentiment analysis process categorized the text as being positive or negative. Finally, statistical analysis was conducted on the outcome of the sentiment analysis.
A significant contribution of the current work was extending Kent and Taylor's (1998) Dialogic Loop Theory, which was designed specifically for identifying the relationship building capabilities of a Web site, to encompass the microblogging concept used in Twitter. Specifically, Dialogic Loop Theory is applied and enhanced to develop a model for social media communication to augment relationship building capabilities, which the current study established as a new form for evaluating Twitter tweets, labeled in the current body of work as Microblog Dialogic Communication. The implication is that by using Microblog Dialogic Communication, a college can address and correct their microblogging sentiment.
The results of the data collected found that rural colleges tweeted more positive sentiment tweets and less negative sentiment tweets when compared to the urban colleges tweets.
Pons, Eugene H., "Twitter Activity Of Urban And Rural Colleges: A Sentiment Analysis Using The Dialogic Loop" (2019). FIU Electronic Theses and Dissertations. 4342.
Communication Technology and New Media Commons, Educational Technology Commons, Mass Communication Commons, Social Media Commons
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).