Skip to Main content Skip to Navigation
Conference papers

IRISA at DeFT 2015: Supervised and Unsupervised Methods in Sentiment Analysis

Vedran Vukotić 1 Vincent Claveau 1 Christian Raymond 1
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : In this work, we present the participation of IRISA Linkmedia team at DeFT 2015. The team participated in two tasks: i) valence classification of tweets and ii) fine-grained classification of tweets (which includes two sub-tasks: detection of the generic class of the information expressed in a tweet and detection of the specific class of the opinion/sentiment/emo-tion. For all three problems, we adopt a standard machine learning framework. More precisely, three main methods are proposed and their feasibility for the tasks is analyzed: i) decision trees with boosting (bonzaiboost), ii) Naive Bayes with Okapi and iii) Convolutional Neural Networks (CNNs). Our approaches are voluntarily knowledge free and text-based only, we do not exploit external resources (lexicons, corpora) or tweet metadata. It allows us to evaluate the interest of each method and of traditional bag-of-words representations vs. word embeddings. Mots-clés : Fouille d'opinion, apprentissage artificiel, boosting, apprentissage bayésien, plongement de mots.
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download
Contributor : Vincent Claveau <>
Submitted on : Thursday, March 17, 2016 - 1:11:32 PM
Last modification on : Monday, March 29, 2021 - 2:41:29 PM
Long-term archiving on: : Sunday, June 19, 2016 - 3:01:40 AM


Files produced by the author(s)


  • HAL Id : hal-01226528, version 2


Vedran Vukotić, Vincent Claveau, Christian Raymond. IRISA at DeFT 2015: Supervised and Unsupervised Methods in Sentiment Analysis. DeFT, Défi Fouille de Texte, joint à la conférence TALN 2015, Jun 2015, Caen, France. ⟨hal-01226528v2⟩



Record views


Files downloads