PhD Study : Analysing the impact of fake news upon sentiment in the financial markets

This project is funded by:

CME Group Foundation

Summary

Research has analyzed the power of investor sentiment on asset prices due to the well-known psychological fact that people with high (low) sentiment tend to make overly optimistic (pessimistic) judgments and choices (Baker, et al., 2012; Huang et al., 2009). Significant evidence suggests that investor sentiment pays a significant role in trading; the question is no longer whether investor sentiment affects stock prices, but rather how to measure investor sentiment and quantify its effects? However sentiment is often influenced by social media and online news, but how much can we rely on such sources? With fake news becoming a prominent issue in society, we need to consider the potential impact of fake news upon investor sentiment.

Investment in Bitcoin and the other cryptocurrencies such as Ethereum and Ripple presents particular challenges for investors with no obvious fundamentals upon which to estimate value in contrast to equity investments. Consequently there may be more of a role for sentiment and hence an impact for fake news in influencing both value and volatility given the excessively high cryptocurrency returns reported in recent periods. In this project, building on recent research (Conroy, Rubin and Chen, 2015), we will develop algorithms to explore the detection of fake news. These will be a combination of information retrieval from linguistic descriptions and artificial intelligence based approaches. Correspondences between fake news and investor sentiment in social media, chat boards, newspapers etc., will be established and the impact on cryptocurrency prices determined.

The aim is to develop intelligent text processing and analysis tools to process news and determine its authenticity. A key aspect of price change initially will be a rapid increase in the number of posts on a discussion board and then to analyse whether the sentiment is negative or positive. Concurrently, we will analyse the behaviour of the CRIX index and related news postings and establish trends and correlations between fake news, sentiment and pricing. We can then learn from this to readily detect fake news and prevent market manipulation behaviours in real-time pricing. On successful completion, these algorithms will be extended to the global markets and related news feeds, for example the algorithms will be extended for use on NYSE and NASDAQ using an increased number of bulletin boards and online resources.

General aims of the proposal are:

*Review existing literature in the field;

*Develop artificial intelligence algorithms for the detection of fake news;

*Determine the impact of fake news on investor sentiment;

*Focus upon sentiment within the crypto currency markets

*Determine the impact of fake news on price changes and hence potential market manipulation;

*Utilisation of the CRIX Index and Bitcoin.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

Experience using research methods or other approaches relevant to the subject domain
Sound understanding of subject area as evidenced by a comprehensive research proposal
A comprehensive and articulate personal statement

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

Experience using research methods or other approaches relevant to the subject domain
Sound understanding of subject area as evidenced by a comprehensive research proposal
A comprehensive and articulate personal statement