Welter, Felix J.M.Becker, Michael2021-03-092021-03-092020978-3-88579-750-0https://dl.gi.de/handle/20.500.12116/35782Sentiment classification is either based on sentiment lexicons or machine learning. For the construction and improvement of sentiment lexicons, several approaches and algorithms have been designed. The resulting lexicons are commonly benchmarked in different tasks and compared by their respective performance. However, this measure depends on the application domain. This work proposes a method for context-independent comparison of sentiment lexicons. Three scoring methods for similarity measurement of lexicons are explained. Furthermore, exemplarily applications of the scores are shown, including lexicon similarity analysis before and after expansion via a Distributional Thesaurus and clustering of lexicons. Adaptability and limitations of the lexicon overlap score and the demonstrated applications are discussed.ensentiment analysissentiment classificationsemantic orientationsentiment lexiconspolarity lexiconslexicon similaritylexicon distancelexicon overlap scoreText/Conference Paper1614-3213