The world is now connected to news and information everywhere, narrowing the gap between locations and accelerating the speed of information processing. Data scientists and financial experts are trying to catch up with these evolutions by automating the extraction of sentiment from news. In simpler words, Sentiment Analysis is used to understand the reaction of a person or a group of people to a particular news item. Sentiment analysis is an emerging area where structured and unstructured data is analyzed to generate useful insights leading to improved performances. Information obtained from multiple sources including news wires, macro-economic announcements, social media, micro blogs /twitter, online (search) information such as Google trends and Wikipedia influence both business intelligence and performance evaluation. This sentiment data can help investors and finance professionals to exploit the market and manage their risk exposure.
There is continuous research on this topic by experts all over the world and therefore development in this field is also fast gaining momentum in the Finance industry. During the conference, Prof Tobias Preis, of University of Warwick, answered two questions. The first, can big data resources provide insights into crises in financial markets and the second, can we provide insight into international differences in economic wellbeing by comparing patterns of interaction with the Internet?
In the ‘Handbook of Sentiment Analysis in Finance,’ Professor Gautam Mitra has described a model by which we can measure the impact of sentiment. This handbook was also launched on the 10th of March during the conference on Sentiment Analysis in Finance in Singapore, where many contributors were also present.
Focusing on social media, Prof Enza Messina, co-founder of Sharper Analytics, researches into Twitter and carries out text and network analysis for sentiment mining. Sharing her research results, she discussed how social relationships can be managed to improve user-level sentiment analysis of micro blogs. Weibo (the Chinese equivalent to Twitter) has also been studied to find out sentiments within China. The Chinese equity market has seen an increase in the number of retail investors in recent years, raising interest for Eric Tham, Director of Quantitative Strategies at iMaibo. Analysing two sources of domestic online media-news and social blogs media- Eric determines the factors that have led to this change and discussed the same during the conference.
Commodity trading is yet another application for sentiment analysis, as it is important to understand whether news sentiment affects commodity prices and if yes, how do they do so? Answering this question in her talk, Svetlana Borovkova explained how to make profitable trading strategies and avoid the downside.
Ashok Banerjee, Departmental Head of Finance and Control, explained how the research in the Finance lab of IIM Calcutta has shown that the effect of any news on financial markets depends on the attention of investors. This follows the simple logic that processing any attention-grabbing event requires effort and in absence of that effort (Attention), data (Sentiment) can be missed. Elijah DePalma of Thomson Reuters shed light upon his findings with working on sentiment for the Japanese language.
To obtain conference material, contact us on firstname.lastname@example.org