Abstract
Given a textual resource (e.g. post, review, comment), how can we spot the expressed sentiment? What will be the core information to be used for accurately capturing sentiment given a number of textual resources? Here, we introduce an approach for extracting and aggregating information from different text-levels, namely words and sentences, in an effort to improve the capturing of documents’ sentiments in relation to the state of the art approaches. Our main contributions are: (a) the proposal of two semantic aware approaches for enhancing the cascaded phase of a sentiment analysis process; and (b) MultiSpot, a multilevel sentiment analysis approach which combines word and sentence level features. We present experiments on two real-world datasets containing movie reviews.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
BoW model: represents a document as a set of its words.
- 2.
NB bigrams: Naive Bayes log-count ratios of bigram features.
- 3.
It is used to test differences between different samples.
- 4.
Explores the groups of data that differ after a statistical test of multiple comparisons, e.g. the Friedman test.
References
Coates, A., Ng, A.Y.: Learning feature representations with K-means. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 561–580. Springer, Heidelberg (2012)
Dahl, G.E., et al.: Training restricted boltzmann machines on word observations (2012). arXiv preprint arXiv:1202.5695
Fan, R.-E., et al.: LIBLINEAR: a library for large linear classification. Mach. Learn. Res. 9, 1871–1874 (2008)
Godbole, N., et al.: Largescale sentiment analysis for news and blogs. In: Proceedings of the Conference on Weblogs and Social Media (ICWSM). Citeseer (2007)
Lazebnik, S., et al.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178. IEEE (2006)
Le, Q.V., et al.: Distributed Representations of Sentences and Documents (2014). arXiv preprint arXiv:1405.4053
Maas, A.L., et al.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, pp. 142–150 (2011)
MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)
Martineau, J., et al.: Delta TFIDF: An improved feature space for sentiment analysis. In: ICWSM (2009)
Paltoglou, G., et al.: A study of information retrieval weighting schemes for sentiment analysis. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1386–1395 (2010)
Pang, B., et al.: A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the 42nd annual meeting on Association for Computational Linguistics, p. 271 (2004)
Pang, B., et al.: Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 115–124 (2005)
Shiyang, W., et al.: Emotion classification in microblog texts using class sequential rules. In: 28th AAAI Conference on Artificial Intelligence (2014)
Socher, R., et al.: Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1201–1211 (2012)
Socher, R., et al.: Semi-supervised recursive autoencoders for predicting sentiment distributions. In: Proceedings of the Conference on EMNLP, pp. 151–161 (2011)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the Conference on EMNLP, pp. 1631–1642. Citeseer (2013)
Turney, P.D., et al.: From frequency to meaning: Vector space models of semantics. Artif. Intell. Res. 37(1), 141–188 (2010)
Wang, H., et al.: Sentiment classification of online reviews: using sentence-based language model. JETAI 26(1), 13–31 (2014)
Wang, S., et al.: Baselines and bigrams: Simple, good sentiment and topic classification. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers, Vol. 2, pp. 90–94 (2012)
Whitelaw, C., et al.: Using appraisal groups for sentiment analysis. In: Proceedings of ACM Conference on Information and knowledge management, pp. 625–631. ACM (2005)
Zhang, C., et al.: Sentiment analysis of chinese documents: from sentence to document level. JASIST 60(12), 2474–2487 (2009)
Zhang, W., et al.: Learning non-redundant codebooks for classifying complex objects. In: Proceedings of the 25th Conference on Machine learning, pp. 1241–1248. ICML (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chatzakou, D., Passalis, N., Vakali, A. (2015). MultiSpot: Spotting Sentiments with Semantic Aware Multilevel Cascaded Analysis. In: Madria, S., Hara, T. (eds) Big Data Analytics and Knowledge Discovery. DaWaK 2015. Lecture Notes in Computer Science(), vol 9263. Springer, Cham. https://doi.org/10.1007/978-3-319-22729-0_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-22729-0_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22728-3
Online ISBN: 978-3-319-22729-0
eBook Packages: Computer ScienceComputer Science (R0)