Lexical Context for Profiling Reputation of Corporate Entities

Abstract : Opinion and trend mining on micro-blogs like Twitter recently attracted research interest in several fields including Information Retrieval (IR) and Natural Language Processing (NLP). However, the performance of existing approaches is limited by the quality of available training material. Moreover, explaining automatic systems' suggestions for decision support is a difficult task thanks to this lack of data. One of the promising solutions of this issue is the enrichment of textual content using large micro-blog archives or external document collections, e.g. Wikipedia. Despite some advantages in Reputation Dimension Classification (RDC) task pushed by RepLab, it remains a research challenge. In this paper we introduce a supervised classification method for RDC based on a threshold intersection graph. We analyzed the impact of various micro-blogs extension methods on RDC performance. We demonstrated that simple statistical NLP methods that do not require any external resources can be easily optimized to outperform the state-of-the-art approaches in RDC task. Then, the conducted experiments proved that the micro-blog enrichment by effective expansion techniques can improve classification quality. Lexical Context for Profiling Reputation of Corporate Entities. Available from: https://www.researchgate.net/publication/313846200_Lexical_Context_for_Profiling_Reputation_of_Corporate_Entities [accessed Jun 12, 2017].
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01537189
Contributor : Liana Ermakova <>
Submitted on : Monday, June 12, 2017 - 2:24:30 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Thursday, September 14, 2017 - 12:06:50 PM

File

iceis-2017.pdf
Files produced by the author(s)

Identifiers

Citation

Jean-Valère Cossu, Liana Ermakova. Lexical Context for Profiling Reputation of Corporate Entities. Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 2: ICEIS, Apr 2017, Porto, Portugal. ⟨10.5220/0006284505670576⟩. ⟨hal-01537189⟩

Share

Metrics

Record views

389

Files downloads

183