|Title||Analyzing Sentiment Word Relations with Affect, Judgment, and Appreciation|
|Publication Type||Conference Paper|
|Year of Publication||2012|
|Authors||Neviarouskaya, A, Aono, M|
|Editor||Bandyopadhyay, S, Okumura, M|
|Conference Name||2nd Workshop on Sentiment Analysis where AI meets Psychology (SAAIP 2012)|
|Publisher||COLING 2012 Organizing Committee|
In this work, we propose a method for automatic analysis of attitude (affect, judgment, and appreciation) in sentiment words. The first stage of the proposed method is an automatic separation of unambiguous affective and judgmental adjectives from miscellaneous that express appreciation or different attitudes depending on context. In our experiments with machine learning algorithms we employed three feature sets based on Pointwise Mutual Information, word-pattern co-occurrence, and minimal path length. The next stage of the proposed method is to estimate the potentials of miscellaneous adjectives to convey affect, judgment, and appreciation. Based on the sentences automatically collected for each adjective, the algorithm analyses the context of phrases that contain sentiment word by considering morphological tags, high-level concepts, and named entities, and then makes decision about contextual attitude labels.