EVENT FORECASTING THROUGH NEWS SENTIMENT ANALYSIS

MPhil Thesis Defence


Title: "EVENT FORECASTING THROUGH NEWS SENTIMENT ANALYSIS"

By

Mr. Yancheng Hong


Abstract

Forecasting is the process of making statements about events whose actual 
outcomes have not yet been observed. Accurate forecasting will help people 
making right decision and thus save time and effort for the society.

Recently, there are more and more efforts put into designing sophisticated 
models to improve forecasting accuracy. There are time series models, 
qualitative models, and causal models. The techniques have been advanced from 
simple regression to multiple regression, from moving average to trend 
analysis. A number of assertions have been made that more sophisticated models 
yield better forecasting results.

In this thesis, we tried to improve our forecasting accuracy by incorporating 
the sentiment analysis data. We showed that the forecasting for sports betting 
and political events can be significantly improved by using sentiment analysis 
as a pre-processor. The reason is that the sentiment data is generated from a 
wide-covered news sources and can be viewed as an aggregation of a very large 
group of people. As argued by The Wisdom of Crowds, decision draw from 
aggregation of information in groups are often better than those could have 
been made by any single member of the group.

We also showed that with sentiment analysis data, even simple intuitive models, 
like linear regression model and regression model with exponentially weighted 
moving average technique, can generate better results. We also further derived 
profitable strategies for sports betting and accurate forecasting for political 
events. As a result, our experimental results also validated our sentiment 
analysis system em Lydia.

We hope further investigation of the usage of sentiment data in forecasting can 
be performed in different areas, like national economical data forecasting, 
most popular product forecasting, and even Oscar awardee forecasting.


Date:			Wednesday, 30 June 2010

Time:			2:00pm – 4:00pm

Venue:			Room 4483
 			Lifts 25/26

Committee Members:	Prof. Mordecai Golin (Supervisor)
 			Prof. Steven Skiena (Supervisor)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Dr. Ke Yi


**** ALL are Welcome ****