Jiancheng Shen

Gaining competitive intelligence from social media data: Evidence from two largest retail chains in the world

– Social media analytics uses data mining platforms, tools and analytics techniques to collect, monitor and analyze massive amounts of social media data to extract useful patterns, gain insight into market requirements and enhance business intelligence. The purpose of this paper is to propose a framework for social media competitive intelligence to enhance business value and market intelligence. , – The authors conducted a case study to collect and analyze a data set with nearly half million tweets related to two largest retail chains in the world: Walmart and Costco in the past three months during December 1, 2014-February 28, 2015. , – The results of the case study revealed the value of analyzing social media mentions and conducting sentiment analysis and comparison on individual product level. In addition to analyzing the social media data-at-rest, the proposed framework and the case study results also indicate that there is a strong need for creating a social media data application that can conduct real-time social media competitive intelligence for social media data-in-motion. , – So far there is little research to guide businesses for social media competitive intelligence. This paper proposes a novel framework for social media competitive intelligence to illustrate how organizations can leverage social media analytics to enhance business value through a case study.

A bilingual approach for conducting Chinese and English social media sentiment analysis

Propose a bilingual approach for conducting social media sentiment analysis.Test the approach with movie reviews collected from online social network sites.Experiments show that the proposed approach is effective and has high accuracy. Due to the advancement of technology and globalization, it has become much easier for people around the world to express their opinions through social media platforms. Harvesting opinions through sentiment analysis from people with different backgrounds and from different cultures via social media platforms can help modern organizations, including corporations and governments understand customers, make decisions, and develop strategies. However, multiple languages posted on many social media platforms make it difficult to perform a sentiment analysis with acceptable levels of accuracy and consistency. In this paper, we propose a bilingual approach to conducting sentiment analysis on both Chinese and English social media to obtain more objective and consistent opinions. Instead of processing English and Chinese comments separately, our approach treats review comments as a stream of text containing both Chinese and English words. That stream of text is then segmented by our segment model and trimmed by the stop word lists which include both Chinese and English words. The stem words are then processed into feature vectors and then applied with two exchangeable natural language models, SVM and N-Gram. Finally, we perform a case study, applying our proposed approach to analyzing movie reviews obtained from social media. Our experiment shows that our proposed approach has a high level of accuracy and is more effective than the existing learning-based approaches.

Stock Return Predictability and Investor Sentiment: A High-Frequency Perspective

We explore the predictive relation between high-frequency investor sentiment and stock market returns. Our results are based on a proprietary dataset of high-frequency investor sentiment, which is computed based on a comprehensive textual analysis of sources from news wires, internet news sources, and social media. We find substantial evidence that intraday S&P 500 index returns are predictable using lagged half-hour investor sentiment. The predictive power is also found in other stock and bond index ETFs. We document that this sentiment effect is independent of the intraday momentum effect, which is based on lagged half-hour returns. While the intraday momentum effect only exists in the last half hour, the sentiment effect persists in at least the last two hours of a trading day. From an investment perspective, high-frequency investor sentiment also appears to have significant economic value when evaluated with market timing trading strategies. We find evidence that the return predictability is most likely driven by the trading activities of noise traders.

News and Social Media Emotions in the Commodity Market

Purpose - Emotion plays a significant role in both institutional and individual investors’ decision making process. Emotions affect the perception of risk and the assessment of monetary value. However, there is a lack of empirical evidence available that addresses how investors’ emotions affect commodity market returns. This paper investigates whether media-based emotions can be used to predict future commodity returns. Design/methodology/approach - We examine the short-term predictive power of media-based emotion indices on the following five days’ commodity returns. The research adopts a proprietary dataset of commodity specific market emotions, which is computed based on a comprehensive textual analysis of sources from newswires, Internet news sources, and social media. Time series econometrics models (Threshold-GARCH and VAR) are employed to analyze fourteen years (01/1998-12/2011) of daily observations of the CRB commodity market index, crude oil and gold returns, and the market-level sentiment and emotions (optimism, fear, and joy). Findings - The empirical results suggest that the commodity specific emotions (optimism, fear, and joy) have significant influence on individual commodity returns, but not on commodity market index returns. Additionally, the research findings support the short-term predictability of the commodity specific emotions on the following five days’ individual commodity returns. Compared to the previous studies of news sentiment on commodity returns (Borovkova, 2011; Borovkova and Mahakena, 2015; Smales, 2014), this research provides further evidence of the effects of news and social media based emotions (optimism, fear and joy) in the commodity market. Additionally, this work proposes that market emotion incorporates both a sentimental effect and appraisal effect on commodity returns. Empirical results are shown to support both the sentimental effect and appraisal effect when market sentiment is controlled in crude oil and gold spot markets. Originality/value - This paper adopts the valence-arousal approach and cognitive appraisal approach to explain financial anomalies caused by investor emotions. Additionally, this is the first paper to explore the predictive power of investor emotions (optimism, fear and joy) on commodity returns.