Abstract: SentiStrength? is a well-known tool for opinion mining texts circulated in social networks. There are English, Spanish, Russian versions of SentiStrength?, which demonstrated their advantages in numerous examples. In the paper we present our classifier of opinions for analysis of comments from the Peruvian Facebook and Twitter. We corrected and enriched SentiStrength? Spanish vocabularies having in view the properties of Peruvian Spanish. We also slightly modified the SentiStrength? algorithm rules. We demonstrate the results we have reached with our classifier and SentiStrength?. The experimental results are competitive with traditional approaches developed in this area, and the total accuracy proved to be 72%.

Keywords: SentiStrength?, Opinion Mining, Facebook and Twitter

Link:

SPANISH SENTISTRENGTH AS A TOOL FOR OPINION MINING PERUVIAN FACEBOOK AND TWITTER

Roque López, Javier Tejada, MikeThelwall?

http://foibg.com/ibs_isc/ibs-27/ibs-27-p15.pdf