TRAP@NCI

An Analysis of the Relationship between Twitter feeds and Stock Market Movement

Walsh, Philip (2014) An Analysis of the Relationship between Twitter feeds and Stock Market Movement. Diploma thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Diploma)
Download (1MB) | Preview

Abstract

With the proliferation of Twitter as a source of data through its API and with the use of natural language processing, sentiment analysis has become an insightful way of understanding trends of public opinion and various subject matter. Twitter is used by millions daily thus providing an appropriate supply of relevant data for opinion mining. Techniques that have been developed with natural language processing provide the tools to analyse this data in a meaningful way.

In this paper, I investigate the relationship between Twitter feed content and stock market movement with respect to a specified stock. The specific aim is to identify if the sentiment information deduced from the Twitter feeds has a correlation with the stock price changes over a specified period of time and whether this could be used to predict future shifts in prices by analyzing and study different trends. To achieve this, a quantitative model is constructed to index the polarity of the sentiment of the data retrieved from the Twitter feed using Twitter’s API. A numeric figure rating is assigned to the data so that an assessment can be made on any potential correlation. It is a time-series analysis and the data is sourced daily over a period of five days with a sentiment rating computed each day. The Yahoo API will be used to source the trade data for the stock over this period of time. The share price of the specified stock over this period of five days is graphed against the time-series sentiment rating of the stock, and inferences will then be made on the results of this.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 16 Dec 2014 14:32
Last Modified: 16 Dec 2014 14:32
URI: http://trap.ncirl.ie/id/eprint/1890

Actions (login required)

View Item View Item