Nathalie Le Brun

Extracting semantic relations via the combination of inferences, schemas and cooccurrences

Extracting semantic relations from texts is a good way to build and supply a knowledge base, an indispensable resource for text analysis. We propose and evaluate the combination of three ways of producing lexical-semantic relations.

Mixing Crowdsourcing and Graph Propagation to Build a Sentiment Lexicon: Feelings Are Contagious

This paper describes a method for building a sentiment lexicon. Its originality is to combine crowdsourcing via a Game With A Purpose (GWAP) with automated propagation of sentiments through a spreading algorithm, both using the lexical JeuxDeMots network as data source and substratum. We present the game designed to collect sentiment data, and the principles and assumptions underlying the action of the algorithm that propagates them within the network. Finally, we give a qualitative evaluation of the data obtained for both the game and the spreading done by the algorithm.