SentiSense Affective Lexicon

The SentiSense Affective Lexicon is a concept-based affective lexicon. It is intended to be used in sentiment analysis-related tasks, especially in polarity and intensity classification and emotion identification. SentiSense attaches emotional meanings to concepts from the WordNet lexical database, instead of terms, thus allowing addressing the word ambiguity problem using one of the many WordNet-based word sense disambiguation algorithms. SentiSense is available in English and Spanish.

The SentiSense Affective Lexicon consists of synsets from WordNet labeled with an emotional category. The main part of the lexicon consists of nouns and adjectives, followed by verbs and a small set of adverbs. SentiSense consists of two data files in XML:

  • The first file, SentiSense_Categories.xml, defines the emotional categories and the antonym relationship between them.
  • The second file, SentiSense_Synsets.xml, contains the WordNet synsets that make up the lexicon. In this file, each entry contains the WordNet synset identifier (SID), its part of speech (POS), its gloss or definition in WordNet and the emotional category assigned to it.

SentiSense has been developed semi-automatically using several semantic relations between synsets in WordNet. SentiSense is endowed with a set of tools that allow users to visualize the lexicon and some statistics about the distribution of synsets and emotions in SentiSense, as well as to easily expand the lexicon.

SentiSense in English WordNet 2.1

The SentiSense Affective Lexicon in English for WordNet 2.1 consists of 5,496 words and 2,190 synsets. SentiSense Affective Lexicon is available for research purpose.

Please if you use the corpus cite:

  • Jorge Carrillo-de-Albornoz, Laura Plaza, Pablo Gervás. 2012. SentiSense: An easily scalable concept-based affective lexicon for Sentiment Analysis. In proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012).

 

 

SentiSense in English WordNet 3.0

In order to update SentiSense to the WordNet 3.0 we have automatically updated the synsets to their WordNet 3.0 version using the WordNet mappings. In particular, for nouns and verbs we use the mappings provided by the WordNet team and for adjectives and adverbs, the UPC mappings. In this automatic process we have only found 15 labeled synsets without a direct mapping, which were removed in the new SentiSense version. SentiSense Affective Lexicon is available for research purpose.

Please if you use the corpus cite:

  • Jorge Carrillo-de-Albornoz, Laura Plaza, Pablo Gervás. 2012. SentiSense: An easily scalable concept-based affective lexicon for Sentiment Analysis. In proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012).
  • Jorge Carrillo-de-Albornoz, Irina Chugur, Enrique Amigó. 2012. Using an Emotion-based Model and Sentiment Analysis Techniques to Classify Polarity for Reputation. In proceedings CLEF 2012 Labs and Workshop Notebook Paper.

 

 

SentiSense in Spanish WordNet 3.0

In order to translate the SentiSense English version to Spanish we use the Multilingual Central Repository (MRC). The MCR is an open source database that integrates WordNet versions for five different languages: English, Spanish, Catalan, Basque and Galician. The Inter-Lingual-Index (ILI) allows the automatic translation of synsets from one language to another. SentiSense Affective Lexicon is available for research purpose.

Please if you use the corpus cite:

  • Jorge Carrillo-de-Albornoz, Laura Plaza, Pablo Gervás. 2012. SentiSense: An easily scalable concept-based affective lexicon for Sentiment Analysis. In proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012).
  • Jorge Carrillo-de-Albornoz, Irina Chugur, Enrique Amigó. 2012. Using an Emotion-based Model and Sentiment Analysis Techniques to Classify Polarity for Reputation. In proceedings CLEF 2012 Labs and Workshop Notebook Paper.