About
13
Publications
11,950
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,000
Citations
Publications
Publications (13)
This study examines analyst information intermediary roles using a textual analysis of analyst reports and corporate disclosures. We employ a topic modeling methodology from computational linguistic research to compare the thematic content of a large sample of analyst reports issued promptly after earnings conference calls with the content of the c...
We document that textual discussions in a sample of 363,952 analyst reports provide information to investors beyond that in the contemporaneously released earnings forecasts, stock recommendations, and target prices, and also assist investors in interpreting these signals. Cross-sectionally, we find that investors react more strongly to negative th...
In this study, we employ an advanced topic modeling methodology from computational linguistic research to compare and contrast the thematic content of a large sample of analyst reports to that of conference calls. This methodology allows us to explicitly identify and empirically quantify the amount of information analysts discover and interpret in...
We use the naïve Bayes machine learning approach to extract opinions from the text of 363,952 analyst reports. We show that analyst report text provides information beyond the earnings forecasts, stock recommendations and target prices released contemporaneously (i.e., the quantitative summary measures). Investors react significantly more strongly...
This paper tries to study online word-of-mouth (WOM) effect from a holistic perspective. We associate 303 new-release books' sales data from Amazon.com, Barnesandnoble.com, with WOM data from Amazon and Barnes &Noble reviews, Google Blog Search and Twitter.com. Our empirical results show that WOM of online reviews, blogs, and tweets have orthogonal...
Initially popularized by Amazon.com, recommendation technologies have become widespread over the past several years. However, the types of recommendations available to the users in these recommender systems are typically determined by the vendor and therefore are not flexible. In this paper we address this problem by presenting the recommendation q...
This paper demonstrates that "social network collaborative filtering" (SNCF), wherein user-selected like-minded alters are used to make predictions, can rival traditional user-to-user collaborative filtering (CF) in predictive accuracy. Us-ing a unique data set from an online community where users rated items and also created social networking link...
This paper reports on a preliminary empirical study comparing methods for collaborative filtering (CF) using explicit consumers' social networks. As user-generated social networks become increasingly important and visible in technology-mediated consumer interactions, we can begin to ask how the rich associated information can be used to improve inf...
Writeprint-based identification is getting very popular in crime investigations due to increasing cybercrime incidents, and unavailability of fingerprints in cybercrime. Writeprint is composed of multiple features, such as vocabulary richness, length of sentence, use of function words, layout of paragraphs, and keywords. These writeprint features c...
With the rapid proliferation of Internet technologies and applications, misuse of online messages for inappropriate or illegal purposes has become a major concern for society. The anonymous nature of online-message distribution makes identity tracing a critical problem. We developed a framework for authorship identification of online messages to ad...
The concern about national security has increased significantly since the 9/11 attacks. However, information overload hinders the effective analysis of criminal and terrorist activities. Data mining applied in the context of law enforcement and intelligence analysis holds the promise of alleviating such problems. In this paper, we review crime data...
Criminals have been using the Internet to distribute a wide range of illegal materials globally in an anonymous manner, making
criminal identity tracing difficult in the cybercrime investigation process. In this study we propose to adopt the authorship
analysis framework to automatically trace identities of cyber criminals through messages they pos...
Initially popularized by Amazon.com, recommendationtechnologies have become widespread over the pastseveral years, both in the industry and academia. Thetraditional two-dimensional approach to recommendersystems, involving the dimensions of Users and Items, hasbeen subsequently extended to the multidimensionalapproach supporting additional contextu...