@unpublished{cogprints2322,
           title = {Unsupervised Learning of Semantic Orientation from a Hundred-Billion-Word Corpus},
          author = {Peter D. Turney and Michael L. Littman},
            year = {2002},
             url = {http://cogprints.org/2322/},
        abstract = {The evaluative character of a word is called its semantic orientation. A positive semantic orientation implies desirability (e.g., "honest", "intrepid") and a negative semantic orientation implies undesirability (e.g., "disturbing", "superfluous"). This paper introduces a simple algorithm for unsupervised learning of semantic orientation from extremely large corpora. The method involves issuing queries to a Web search engine and using pointwise mutual information to analyse the results. The algorithm is empirically evaluated using a training corpus of approximately one hundred billion words ? the subset of the Web that is indexed by the chosen search engine. Tested with 3,596 words (1,614 positive and 1,982 negative), the algorithm attains an accuracy of 80\%. The 3,596 test words include adjectives, adverbs, nouns, and verbs. The accuracy is comparable with the results achieved by Hatzivassiloglou and McKeown (1997), using a complex four-stage supervised learning algorithm that is restricted to determining the semantic orientation of adjectives. }
}

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>