Application of Semantic Network Theory to Mine Aspect Terms and Opinion Knowledge from Online reviews

Sudhir Namdeorao Dhage 1, Alfiya Shama 2

Abstract


Reviews posted online pose as a boon to the public for making simple to complex decisions of their life like buying a particular brand of shampoo, pursuing a career choice, booking a movie ticket and visiting a restaurant. There is too much information available but not all can be read by a single user. Some form of summarization involving only the relevant features needs to be available in highlighted form. Existing work either follows a supervised approach or makes use of the pre-developed dictionaries to build a summarization framework. In this paper, an unsupervised approach dependent on cognitive understanding and semantic network theory to mine out the most generic aspect terms or categories from the text based reviews written by users. The Aspect Category Identification (ACI) framework built mines for the terms in the reviews that are most spoken, compares two brands based on the reviews posted in terms of how positive or negative folks are on that particular brand and lastly explores the opinion people hold for a particular target by filtering out the opinion words from the reviews. Experiments held by making use of three different datasets involving a purely product oriented Laptop dataset and a purely service oriented Restaurant dataset both from SemEval 2015 and the last one Customer Review Dataset which is a blend of many products and services. An F1- score of 67% is obtained on evaluation with other baseline methods.


Keywords


Summarization; Unsupervised; Aspect Category Identification (ACI); Customer Review Dataset; F1- score

Full Text:

PDF

References


Priya V, Umamaheswari K. Ensemble based parallel k means using map reduce for aspect based summarization. Proceedings of the International Conference on Informatics and Analytics, ICIA 2016, Pondicherry, India, ACM, New York, NY, USA, 2016; 1-9.

Soni S, Sharaff A. Sentiment analysis of customer reviews based on hidden markov model. Proceedings of the 2015 International Conference on Advanced Research in Computer Science Engineering and Technology ICARCSET ’15, Unnao, India, ACM, New York, NY, USA, 2015; 1-5.

Suresh V, Roohi S, Eirinaki M. Aspect-based opinion mining and recommendation system for restaurant reviews. Proceedings of the 8th ACM Conference on Recommender systems - RecSys ’14, Foster City, Silicon Valley, California, USA, ACM, New York, NY, USA, 2014; 361-362.

Schouten K, Frasincar F. Survey on aspect-level sentiment analysis. IEEE Transactions on Knowledge and Data Engineering, March 1, 2016; 813-830.

Pablos GA, Cuadros M, Rigau G. W2VLDA: Almost unsupervised system for aspect based sentiment analysis. Expert Systems with Applications, 2018; 8: 127-137.

Akhtar MS, Gupta D, Ekbal A, et al. Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis. Knowledge-Based Systems, 2017; 125: 116-135.

Anand D, Naorem D. Semi-supervised aspect based sentiment analysis for movies using review filtering. Procedia Computer Science, 2016; 84: 86-93.

Gao B, Hu N, Bose I. Follow the herd or be myself? An analysis of consistency in behavior of reviewers and helpfulness of their reviews. Decision Support Systems, 2017; 95: 1-11.

Gavilanes FM, Lopez AT, Martinez JJ, et al. Unsupervised method for sentiment analysis in online texts. Expert Systems with Applications, 2016; 58: 57-75.

Medhat W, Hassan A, Korashy H. Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 2014; 5(4): 1093-1113.

Chua AY, Banerjee S. Helpfulness of user-generated reviews as a function of review sentiment, product type and information quality. Computers in Human Behavior, 2016; 54: 547-554.

Marstawi A, Sharef NM, Aris T, et al. Ontology-based aspect extraction for an improved sentiment analysis in summarization of product reviews. Proceedings of the 8th International Conference on Computer Modeling and Simulation ICCMS ’17, ACM, New York, NY, USA, 2017; 100-104.

Perikos I, Hatzilygeroudis I. Aspect based sentiment analysis in social media with classifier ensembles. 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), Wuhan, 2017; 273-278.

Tsai YL, Wang YC, Chung CW, et al. Aspect-category based sentiment classification with aspect-opinion relation. 2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI), Hsinchu, 2016; 162-169.

Rahman MM, Wang H. Hidden topic sentiment model. Proceedings of the 25th International Conference on World Wide Web-(WWW ’16), International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 2016; 155-165.

Rana TA, Cheah YN. A two-fold rule-based model for aspect extraction. Expert Systems with Applications, 2017; 89: 273-285.

Canuto SCA, Gon ̧calves MA, Benevenuto F. Exploiting new sentiment- based meta-level features for effective sentiment analysis. Proceedings of the Ninth ACM International Conference on Web Search and Data Mining - WSDM 16, ACM, New York, NY, USA, 2016; 53-62.

Shama A, Dhage SN. Application of associative network theory to mine relevant aspect terms from customer reviews. 2018 IEEE International Conference on Current Trends Towards Converging Technologies (ICCTCT’18), Coimbatore, India, 2018.

Balachandran L, Kirupananda A. Online reviews evaluation system for higher education institution: An aspect based sentiment analysis tool. 2017 11th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Malabe, 2017; 1-7.

Perikos I, Hatzilygeroudis I. Aspect based sentiment analysis in social media with classifier ensembles. 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS), Wuhan, 2017; 273-278.

Sasmita DH, Wicaksono AF, Louvan S, et al. Unsupervised aspect-based sentiment analysis on Indonesian restaurant reviews. 2017 International Conference on Asian Language Processing (IALP), Singapore, 2017; 383-386.

Shama A, Dhage SN. A meticulous critique on prevailing techniques of aspect-level sentiment analysis. 2018 IEEE International Conference on Current Trends Towards Converging Technologies (ICCTCT’18), Coimbatore, India, 2018.

Dhage SN, Shama A. “An atypical approach for uncovering the essence of emotions in consumer reviews. International Conference on Computer and Information Sciences (ICCOINS’18), Kuala Lumpur, Malaysia, 2018.




DOI: http://dx.doi.org/10.24294/csma.v0i0.895

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.