论文信息 - Prediction of Happy Endings in German Novels

Prediction of Happy Endings in German Novels

Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVMclassifier, which yields an average F1-score of about 73%.

[1] M. Doas,et al. The rest of the story. , 2008, Journal of Christian nursing : a quarterly publication of Nurses Christian Fellowship.

[2] F. Puppe,et al. Automatische Erkennung von Figuren in deutschsprachigen Romanen , 2015, DHd.

[3] Ellen Riloff,et al. Automatically Producing Plot Unit Representations for Narrative Text , 2010, EMNLP.

[4] Saif Mohammad,et al. CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[5] Micha Elsner,et al. Linguistic Issues in Language Technology – LiLT , 2015 .

[6] Saif Mohammad,et al. From Once Upon a Time to Happily Ever After: Tracking Emotions in Novels and Fairy Tales , 2011, LaTeCH@ACL.

[7] Gerhard Heyer,et al. SentiWS - A Publicly Available German-language Resource for Sentiment Analysis , 2010, LREC.

[8] Saif Mohammad,et al. Generating Music from Literature , 2014, CLfL@EACL.

[9] Ulli Waltinger,et al. Sentiment Analysis Reloaded - A Comparative Study on Sentiment Polarity Identification Combining Machine Learning and Subjectivity Features , 2010, WEBIST.

[10] Bo Pang,et al. Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[11] R. Plutchik. A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMOTION , 1980 .