We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text’s opinion towards its main subject matter. We show that SO-CAL’s performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability. 1.

We present a statistical parsing framework for sentence-level sentiment classification in this article. Different from previous work employing linguistic parsing results for sentiment analysis, we develop a statistical parser to directly analyze the sentiment structure of a sentence. We show that the complicated phenomena in sentiment analysis (e.g., negation, intensification, and contrast) can be elegantly handled the same as simple and straightforward sentiment expressions in a unified and probabilistic way. We formulate the sentiment grammar upon Context-Free Grammars (CFGs), and provide a formal description of the sentiment parsing framework. We develop the parsing model to obtain the possible sentiment parsing trees for a sentence, from which the computation model is proposed to derive the sentiment strength and polarity, and the ranking model is dedicated to selecting the best sentiment tree. We train the parser directly from examples of sentences annotated only with sentiment polarity labels but without any syntactic annotations or polarity annotations of the constitutes within the sentences. Therefore we can obtain the training data easily. In particular, we train a sentiment parser, s.parser, from a large amount of review sentences with users ’ ratings as rough sentiment polarity labels. Extensive experiment results on existing benchmark datasets show significant improvements over baseline sentiment classification approaches.

This proposal was presented by

any form or by any means, electronic or mechanical, including photocopying, without written permission from the publisher. Product or company names used in this set are for identification purposes only. Inclusion of the names of the products or companies does not indicate a claim of ownership by IGI Global of the trademark or registered trademark. Library of Congress Cataloging-in-Publication Data

Motivated by methods used in language modeling and grammar in-duction, we propose the use of pragmatic constraints and perplexity as criteria to filter the unlabeled data used to generate the seman-tic similarity model. We investigate unsupervised adaptation algo-rithms of the semantic-affective models proposed in [1, 2]. Affec-tive ratings at the utterance level are generated based on an emo-tional lexicon, which in turn is created using a semantic (similarity) model estimated over raw, unlabeled text. The proposed adaptation method creates task-dependent semantic similarity models and task-dependent word/term affective ratings. The proposed adaptation al-gorithms are tested on anger/distress detection of transcribed speech data and sentiment analysis in tweets showing significant relative classification error reduction of up to 10%. Index Terms — emotion, affect, affective lexicon, polarity de-tection, language understanding. 1.