Semantic feature representation to capture news impact

Boyi Xie, Dingquan Wang, Rebecca J. Passonneau

Research output: Contribution to conferencePaper

1 Scopus citations

Abstract

This paper presents a study where semantic frames are used to mine financial news so as to quantify the impact of news on the stock market. We represent news documents in a novel semantic tree structure and use tree kernel support vector machines to predict the change of stock price. We achieve an efficient computation through linearization of tree kernels. In addition to two binary classification tasks, we rank news items according to their probability to affect change of price using two ranking methods that require vector space features. We evaluate our rankings based on receiver operating characteristic curves and analyze the predictive power of our semantic features. For both learning tasks, the proposed semantic features provide superior results.

Original languageEnglish (US)
Pages231-236
Number of pages6
Publication statusPublished - Jan 1 2014
Event27th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2014 - Pensacola, United States
Duration: May 21 2014May 23 2014

Other

Other27th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2014
CountryUnited States
CityPensacola
Period5/21/145/23/14

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computer Science Applications

Cite this

Xie, B., Wang, D., & Passonneau, R. J. (2014). Semantic feature representation to capture news impact. 231-236. Paper presented at 27th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2014, Pensacola, United States.