Separating Actor-View from Speaker-View Opinion Expressions using Linguistic Features

Proceedings of NAACL-HLT 2016, pages 778–788, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Separating Actor-View from Speaker-View Opinion Expressions using Linguistic Features Michael Wiegand and Marc Schulder Spoken Language Systems Saarland University D-66123 Saarbr¨ucken, Germany michael.wiegand@lsv.uni-saarland.de marc.schulder@lsv.uni-saarland.de Josef Ruppenhofer Dept. of Information Science and Language Technology Hildesheim University D-31141 Hildesheim, Germany ruppenho@uni-hildesheim.de Abstract We examine different features and classifiers for the categorization of opinion words into actor and speaker view. To our knowledge, this is the first comprehensive work to address sentiment views on the word level taking into consideration opinion verbs, nouns and adjec- tives. We consider many high-level features requiring only few labeled training data. A de- tailed feature analysis produces linguistic in- sights into the nature of sentiment views. We also examine how far global constraints be- tween different opinion words help to increase classification performance. Finally, we show that our (prior) word-level annotation corre- lates with contextual sentiment views. 1 Introduction While there has been much research in sentiment analysis on the tasks of subjectivity detection and polarity classification, there has been less work on other types of categorizations that can be imposed upon subjective expressions. In this paper, we focus on the views that an opin- ion expression evokes. By views, we understand the perspective of the holder of some opinion. We dis- tinguish between the two most common types: ex- pressions conveying sentiment of the entities partic- ipating in the event denoted by the opinion word, referred to as actor views (e.g. disappointed in (1) or praised in (2)), and expressions conveying sen- timent of the speaker of the utterance, referred to as speaker views (e.g. excelled in (3) or wasted in (4)). (1) Party members were disappointedactor at the election outcome. (2) All representatives praisedactor the final agreement. (3) Sarah excelledspeaker in virtually every subject. (4) The government wastedspeaker a lot of money. The distinction between those categories is relevant for related tasks in sentiment analysis, most impor- tantly, opinion holder and target extraction. This has already been demonstrated for verbs (Wiegand and Ruppenhofer, 2015). For example, even though the noun Peter has the same grammatical relation to the opinion verb in (5) & (6), in the former sentence it is a holder but in the latter it is a target. Similar cases can be observed for opinion nouns (7) & (8) and opinion adjectives (9) & (10). Only the knowl- edge of sentiment views helps us to assign opinion roles correctly. (5) [Peter]Holder criticizesverb actor Mary. (6) [Peter]Target cheatedverb speaker in the exam. (7) [Peter’s]Holder beliefnoun actor is that all people should be treated equally. (8) [Peter’s]Target misbehaviournoun speaker is unbearable. (9) [Peter]Holder is disappointedadj actor . (10) [Peter]Target is intelligentadj speaker . While the distinction of sentiment views is not new, we put a different emphasis on this task. Our focus is on the prior meaning that opinion words evoke. Hence we consider this as a word-level task. Every opinion word from a sentiment lexicon is to …

Content truncated to 500 words