This paper presents Senti17 system which uses ten convolutional neural networks (ConvNet) to assign a sentiment label to a tweet. The network consists of a convolutional layer followed by a fully-connected layer and a Softmax on top. Ten instances of this network are initialized with the same word embeddings as inputs but with different initializations for the network weights. We combine the results of all instances by selecting the sentiment label given by the majority of the ten voters. This system is ranked fourth in SemEval-2017 Task4 over 38 systems with 67.4% average recall.

In this paper, we present our contribution for the automatic construction of the Scholarly Book Reviews corpora from two different sources, the OpenEdition platform which is dedicated to electronic resources in the humanities and social sciences, and the Web. The main target is the collect of reviews in order to provide automatic links between each review and its potential book in the future. For these purposes, we propose different document representations and we apply some supervised approaches for binary genre classification before evaluating their impact.