Evaluating the morphological compositionality of polarity

Unknown words are a challenge for any NLP task, including sentiment analysis. Here, we evaluate the extent to which sentiment polarity of complex words can be predicted based on their morphological make-up. We do this on German as it has very productive processes of derivation and compounding and many German hapax words, which are likely to bear sentiment, are morphologically complex. We present results of supervised classification experiments on new datasets with morphological parses and polarity annotations.

[1]  Josef Ruppenhofer,et al.  Dimensions of Metaphorical Meaning , 2014, CogALex@COLING.

[2]  C. Osgood,et al.  The Measurement of Meaning , 1958 .

[3]  Mitsuru Ishizuka,et al.  SentiFul: A Lexicon for Sentiment Analysis , 2011, IEEE Transactions on Affective Computing.

[4]  Janyce Wiebe,et al.  Learning Subjective Language , 2004, CL.

[5]  Stephen G. Pulman,et al.  The Good, the Bad, and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words , 2008, ACL.

[6]  Helmut Feldweg,et al.  GermaNet - a Lexical-Semantic Net for German , 1997 .

[7]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[8]  S. Kotz,et al.  Leipzig Affective Norms for German: A reliability study , 2010, Behavior research methods.

[9]  Jessica Rosenberg,et al.  Using the World-Wide Web to obtain large-scale word norms: 190,212 ratings on a set of 2,654 German nouns , 2009, Behavior research methods.

[10]  Mohak Shah,et al.  Evaluating Learning Algorithms: A Classification Perspective , 2011 .

[11]  Manfred Klenner,et al.  PolArt: A Robust Tool for Sentiment Analysis , 2009, NODALIDA.

[12]  Marco Baroni,et al.  Predicting the Components of German Nominal Compounds , 2002, ECAI.

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  Nathan Schneider,et al.  SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM) , 2016, *SEMEVAL.

[15]  Michael Wiegand,et al.  Opinion Holder and Target Extraction on Opinion Compounds - A Linguistic Approach , 2016, HLT-NAACL.

[16]  Yannick Versley,et al.  Subsentential Sentiment on a Shoestring: A Crosslingual Analysis of Compositional Classification , 2015, HLT-NAACL.

[17]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[18]  Amy Beth Warriner,et al.  Concreteness ratings for 40 thousand generally known English word lemmas , 2014, Behavior research methods.

[19]  Michael Wiegand,et al.  Comparing methods for deriving intensity scores for adjectives , 2014, EACL.

[20]  Timothy Baldwin,et al.  Multiword Expressions: A Pain in the Neck for NLP , 2002, CICLing.

[21]  Alexander Geyken,et al.  dlexDB : eine lexikalische Datenbank für die psychologische und linguistische Forschung , 2011 .

[22]  Thierry Declerck,et al.  SentiMerge: Combining Sentiment Lexicons in a Bayesian Framework , 2014, LG-LP@COLING.

[23]  Yair Neuman,et al.  Literal and Metaphorical Sense Identification through Concrete and Abstract Context , 2011, EMNLP.

[24]  Sabine Schulte im Walde,et al.  Automatically Generated Affective Norms of Abstractness, Arousal, Imageability and Valence for 350 000 German Lemmas , 2016, LREC.

[25]  Ulli Waltinger,et al.  GermanPolarityClues: A Lexical Resource for German Sentiment Analysis , 2010, LREC.