http://hdl.handle.net/123456789/957 2026-04-14T23:14:13Z 2026-04-14T23:14:13Z Amoako, Linda http://hdl.handle.net/123456789/11511 2025-01-23T09:34:44Z 2021-07-01T00:00:00Z

Mixing Metaphors, Modifiers And Affect Towards Sentiment Evaluation Amoako, Linda The use of figurative language, with a major emphasis on metaphors and a minor emphasis on oxymorons, has been widely accepted as part of everyday language, not just in literary language. Over the last few years, there has also been a large move towards automated sentiment analysis tlu·ough which diverse corporations seek feedback on the sentiment (or affect: emotions, value judgments, etc.) that customers bear towards their goods and services. The need for this feedback has been particularly challenged by the use of social media, which allow the use of non-literal language, including shorthand, abbreviations and emoticons. Begilming with an overview of metaphors, sentiment analysis, modifiers, and how they relate to each other in terms of conveying affect, this thesis examines the accuracy of relying on lexical libraries like SentiWordNet and WordNet in an attempt to extract sentiment-related information on language in discourse. Following a set of empirical studies and experiments, I examined how some existing systems are carrying out analysis of metaphors and oxymorons, and how those systems evaluate metaphors that have made use of modifiers. I demonstrate that modifiers do enhance the sentiment conveyed by metaphors, though their placement within the metaphor, if not done well, can distort the intended meaning, providing a good motivation for non-literal text identification systems to be integrated into existing sentiment analysis systems. I also prove by analysis that SentiWordNet has inherent inaccuracies that introduce errors in sentiment extractions, and recommend that it is crucial to identify non-literal text before sentiment is extracted in order to avoid incorrect judgments xv, 277p:, ill.

2021-07-01T00:00:00Z Nakpih, Callistus Ireneous http://hdl.handle.net/123456789/7309 2022-01-19T16:07:07Z 2021-02-01T00:00:00Z

Automated Discovery of Fallacies in Legislative Processes Nakpih, Callistus Ireneous This research or study presents a computational logic tool for automatic discovery of fallacies, which may be inherent, or, introduced intentionally or unintentionally in legal texts. Sound reasoning through legal text has always been a challenge in Natural Language Processing (NLP) in Artificial Intelligence (AI) since the fourth century, wich has received different computational approaches for solution. I have explored and presented logic techniques through the formalism of legal text from its natural form to First Order Logic (FOL) and Prolog programme, which results in the provision of clarity, comprehensibility and deductive reasoning of the text. This as well maintains sound reasoning through the text, which supports decision-making process that will always lead to the same conclusions. I formalised the Citizenship Act and the Fundamental Human Rights and Freedom of Ghana as the knowledge base of the system. I also formalised two Supreme Court cases as testbed to the system in FOL, and the formalised text was implemented in Prolog progrmme for the automated reasoning process of the sytem. This allows for the discovery of fallacies in a claim made against an opponent, facts established by the opponent, and the law employed for the legislation of the case in court. I have also presented an algorithmic framework here in pseudocode for the discovery of logical fallacies in the text. The ontology design of the philosophical research methodology was employed in the conduction of this research, which guided the techniques used for the formalism of the logic tool. xi, 312p:, ill.

2021-02-01T00:00:00Z