Spanish Twitter Messages Polarized through the Lens of an English System.
Marlies Santos Deas, Or Biran, Kathleen R. McKeown, Sara Rosenthal · 2015
In this paper we describe the adaptation of a supervised classification system that was originally developed to detect sentiment on Twitter texts written in English. The Columbia University team adapted this system to participate in Task 1 of the 4th edition of the experimental evaluation workshop for sentiment analysis focused on the Spanish language (TASS 2015). The task consists of determining the global polarity of a group of messages written in Spanish using the social media platform Twitter.