Guzman, Sara (2016) Determinants of Politically Charged News in Media: Relationships Between Entity and Sentiment Tonality. Masters thesis, Dublin, National College of Ireland.
PDF (Master of Science)
Download (1MB) | Preview
Politically charged news usually have important and powerful information that is expected to reflect the political situation of an event without bias expectations. As text document type of communication, it reflects emotions and sentiment tonality which recently has become a topic of study and research, not only for linguistics but also for data scientists. These emotions reveal psychological insights about the way the author is presenting the news, their perspective and also, meaningful hiding sentiments in the lexicon. Lexically expressed opinions can be found in news texts. This, represents one of the reason to choose the research topic of this paper, mainly based on the identification of the determinants of politically charged news in media. Specifically, the anger sentiment tonality and the relationship that has with the major entities of the article. For this, Text Mining, Natural Language Processing and Machine Learning played the main role in providing the methodologies and tools to implement for the analysis and hypothesis testing. Decision Trees and Association Rules models were implemented to prove the research hypothesis were true.
|Item Type:||Thesis (Masters)|
|Subjects:||Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
|Divisions:||School of Computing > Master of Science in Data Analytics|
|Depositing User:||CAOIMHE NI MHAICIN|
|Date Deposited:||27 Jan 2017 13:39|
|Last Modified:||27 Jan 2017 13:39|
Actions (login required)