3. Introduction
● The recent burst in the web usage has contributed to
the growth of number of various online reviews.
● Most of the reviews are objective where as some are
context sensitive and subjective.
● All these reviews contain mixture of negative, positive
or neutral comments.
● In today’s world people tend to go through these
online reviews before going ahead with any activities
like shopping, purchasing, and reading a book etc …
● This research aims on assisting the people by
developing an ontology for various online book reviews.
4. Introduction ...
● Ontology is a formal and explicit domain specific
reference model.
● Ontology reference model can be used for defining
set of concepts along with the relationship among
them.
● Therefore this nature provides an efficient way of
performing opinion mining on book reviews.
5. Introduction ...
● General opinion mining's are more
focused on
1. Context-free sentiment classification
2. Large number of manually annotated
training examples.
● This project focuses on context-sensitive opinion
mining system.
6. Contents of Book Review
● Description.
● Narration.
● Exposition.
● Argument.
● State of Knowledge.
● Content Description.
● Subject Area.
8. Ontology Development
● Ontology development is based on the
domain ( Domain Ontology ).
● Task of ontology construction is divided in
to two.
1. Select the relevant sentences including
conceptions.
2. Extract the conceptions from those
sentences.
12. Feature Identification
● This process is used for feature
identification of ontology terminologies.
● Extraction of the related sentence which
contain ontology terminologies.
● Those sentences can be used for feature
extraction.
14. Polarity Identification
● Initially two well known approaches are
considered.
❖ SentiWordNet
❖ WordNet-Affect
● Eventually we decided to use WordNet-
Affect.
15. WordNet-Affect …
● Emotional causes can be calculated in
two different ways.
❖ Direct Affective Words.
❖ Indirect Affective Words.
● Affective weight is calculated based on
semantic similarity mechanism which
acquires from large corpus of texts.
● Semantic Affinity for each emotion is
returned.
18. Sentiment Analysis
● Using the final lists of positive,
negative and neutral words or phrases,
opinion orientation expressed on each
feature can be analyzed.
● Hierarchy structure is used to calculate the
opinion of high level concept.
20. Conclusion
● This research attempts to create an
ontology for the book domain to perform
opinion mining.
● During the opinion mining process, polarity
of the word is being identified by using
WordNet-Affect.
22. References
● Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up?
sentiment classification using machine learning
techniques. In: Proceedings of the Conference on
Empirical Methods in Natural Language Processing,
EMNLP 2002 (2002)
● Popescu, A.M., Etzioni, O.: Extracting product features
and opinions from reviews. In: Proceedings of the
Conference on Empirical Methods in Natural Language
Processing, EMNLP 2005 (2005)
● Hu, M., Liu, B.: Mining and summarizing customer
reviews. In: Proceedings of ACM SIGKDD conference,
KDD 2004 (2004)
23. References ...
● Kaji, N., Kitsuregawa, M.: Automatic construction of
polarity-tagged corpus from html documents. In:
Proceedings of the COLING/ACL on Main conference
poster sessions, Association for Computational Linguistics
Morristown, NJ, USA, pp. 452–459 (2006).
● Hu, M., Liu, B.: Mining opinion features in customer
reviews. In: Proceedings of AAAI, pp. 755–760 (2004).
● Carenini, G., Ng, R., Pauls, A.: Interactive multimedia
summaries of evaluative text. In: Proceedings of the 11th
international conference on Intelligent user interfaces,pp.
124–131. ACM, New York (2006).
24. References ...
● Ding, X., Liu, B.: The utility of linguistic rules in opinion
mining. In: Proceedings of SIGIR 2007 (2007)
● Gruber, T.R.: A translation approach to portable ontology
specifications. Knowledge Acquisition 5, 199–220 (1993)
● Pang, B.: Seeing stars: Exploiting class relationships for
sentiment categorization with respect to rating scales. Ann.
Arbor. 100 (2005).
● Riloff, E., Wiebe, J.: Learning extraction patterns for
subjective expressions. In:Proceedings of the Conference
on Empirical Methods in Natural Language Processing
(EMNLP 2003), pp. 105–112 (2003)
25. References ...
● Turney, P., et al.: Thumbs up or thumbs down? semantic
orientation applied to unsupervised classification of
reviews. In: Proceedings of the 40th annual meeting of the
Association for Computational Linguistics, pp. 417–424
(2002).
● Gamon, M., Aue, A., Corston-Oliver, S., Ringger, E.: Pulse:
Mining customer opinions from free text. In: Famili, A.F.,
Kok, J.N., Pe˜na, J.M., Siebes, A., Feelders, A. (eds.) IDA
2005. LNCS, vol. 3646, pp. 121–132. Springer, Heidelberg
(2005)
● Dave, K., Lawrence, S., Pennock, D.: Mining the peanut
gallery: Opinion extraction and semantic classification of
product reviews. In: Proceedings of the 12th international
conference on World Wide Web, pp. 519–528. ACM, New
26. References ...
● Hearst, M.A.: Direction-based text interpretation as an
information access refinement, pp. 257–274 (1992)
● Jacquemin, C.: Spotting and Discovering Terms through
Natural Language Processing. MIT Press, Cambridge
(2001)
● Kobayashi, N., Inui, K., Matsumoto, Y.: Collecting
evaluative express for opinion extraction. In: Proceedings
of the International Joint Conference on Natural Language
Processing, IJCNLP (2004)
● Yi, J., Bunescu, T.N., Niblack, R.W.: Sentiment analyzer:
extracting sentiments about a given topic using natural
language processing techniques. In: Proceedings of IEEE
International Conference on Data Mining, ICDM 2003
(2003)
27. References ...
● Hatzivassiloglou, V., McKeown, K.: Predicting the semantic
orientation of adjectives. In: Proceedings of ACL-EACL
1997 (1997)
● Kanayama, H., Nasukawa, T.: Fully automatic lexicon
expansion for domainoriented sentiment analysis. In:
Proceedings of the Conference on Empirical Methods in
Natural Language Processing, EMNLP 2006 (2006)
● Esuli, A., Sebastiani, F.: Sentiwordnet: A publicly available
lexical resource for opinion mining. In: Proceedings of 5th
Conference on Language Resources and Evaluation,
LREC 2006 (2006).
● Esuli, A., Sebastiani, F.: Sentiwordnet: A publicly available
lexical resource for opinion mining. In: Proceedings of 5th
Conference on Language Resources and Evaluation,
28. References ...
● Book Review Guidelines. Available at [http://www.write.
armstrong.edu/handouts/BookReview.pdf]. Accessed on
14/12/2013.
● Samaneh Moghaddam & Martin Ester : Mining in Online
Reviews: Recent Trends. Simon Fraser University Tutorial.
● Efstratios Kontopoulos, Christos Berberidis, Theologos
Dergiades, Nick Bassiliades : Ontology-based Sentiment
Analysis of Twitter Posts , Expert Systems with
Applications (2011).
● Natalya F. Noy and Deborah L. McGuinness: Ontology
Development 101: A Guide to Creating Your First
Ontology, Stanford University, Stanford, CA, 94305 ( 2009
)
29. References ...
● A. Valitutti, C. Strapparava, and O. Stock. Developing
affective lexical resources. Psychnology: 2 (1), 2004