News Sentiment Impact Analysis (NSIA) Framework

Abstract

The huge increase in online content has rapidly stepped up the challenges facing various entities such as organisations, businesses, governments. Dealing with this immense increase in information is beyond any human ability, as it requires massive efforts to go through huge volumes of posts/news to analyse and understand their content. In responding to this challenge, research has picked up in recent years to automatically analyse, and extract opinions/sentiment from online content. This thesis investigated the area of sentiment analysis and its impact on financial market entities. The thesis includes a review of the sentiment analysis processes, , an overview of sentiment analysis studies and their application to the financial markets domain. The literature shows a gap in defining systematic and reusable evaluation processes, for users to automatically conduct impact analysis of sentiment datasets in different financial contexts. In addressing the research gap the thesis proposes a framework called News Sentiment Impact Analysis (NSIA) which consists of three components which are a conceptual data model, a software architecture, and a set of use cases. The key component which is the conceptual data model captures three sets of parameters: the financial context parameters, the sentiment related parameters, and the impact measure parameters. The CPD model is supported by a software architecture, which consists of a GUI, Business, and Data layers. The main use case allows the analyst to define the CPD parameters using the provided GUI layer and trigger the impact analysis process. To evaluate the proposed framework, a prototype is implemented. Three case studies have been conducted to evaluate the different aspects of the proposed framework. ORIGINALITY STATEMENT 'I hereby declare that this submission is my own work and to the best of my knowledge it contains no materials previously published or written by another person, or substantial proportions of material which have been accepted for the award of any other degree or diploma at UNSW or any other educational institution, except where due acknowledgement is made in the thesis. Any contribution made to the research by others, with whom I have worked at UNSW or elsewhere, is explicitly acknowledged in the thesis. I also declare that the intellectual content of this thesis is the product of my own work, except to the extent that assistance from others in the project's design and conception or in style, presentation and linguistic expression is acknowledged.'