Aspect-Based Text Summarization Using MapReduce Optimization
Aspect-based summarization techniques require improvement in accuracy of the generated summaries. These systems show significant role in the analysis of web review contents. Also they are useful to analyse the reviews in the web which increases drastically day by day. So the generated summary representing the entire review in a concise manner for each feature or aspect in the reviews would be useful for users. An overview about aspect-based summarization system is provided along with the proposed MapReduce based on node optimization algorithm. The system uses MapReduce framework and an in-node mapper, reducer algorithm is devised for generating summaries. The accuracy of the system-generated summary is better than existing MapReduce-based summarization systems.
KeywordsText summarization MapReduce In-node mapper Optimization Partitioner
- Blake, C. (2006). A comparison of document, sentence and term event spaces. In Joint 21st international conference on Computational Linguistics (COLING) and the 44th annual meeting of the Association for Computational Linguistics (ACL), Sydney, Australia, 17–21 July 2006 (pp. 601–608). New York: ACM.Google Scholar
- Gamon, M., Aue, A., Corston-Oliver, S., & Ringger, E. (2005). Pulse: Mining customer opinions from free text. In Sixth international symposium on Intelligent Data Analysis (IDA), Madrid, Spain, 8–10 September 2005. Paper no. LNCS 3646 (pp. 121–132). Heidelberg: Springer.Google Scholar
- Hotel Datasets. (2001). http://www.text-analytics101.com/. Accessed 22 Jan 2016.
- Jayashri, K., & Mayura, K. (2013). Latent semantic analysis used for Mobile rating and review summarization. International Journal of Computer Science and Telecommunication, 4, 61–67.Google Scholar
- Large Movie Review Dataset. (2001). http://ai.stanford.edu/~amaas/data/sentiment/. Accessed 22 Jan 2016.
- Lin, C. Y. (2004). ROUGE: A package for automatic evaluation summaries. In Workshop on text summarization branches out, Barcelona, Spain, 25–26 July 2004 (pp. 74–81). Barcelona, Spain: ACL.Google Scholar
- Lin, J., & Dyer, C. (2010). Data-intensive text processing with MapReduce. University of Maryland, College Park Manuscript (pp. 28–30). San Rafael: Morgan & Claypool Publishers.Google Scholar
- Priya, V., & Umamaheswari, K. (2016). Ensemble based parallel k means using MapReduce for aspect based summarization. In International conference on informatics and analytics article no 26, Pondicherry, India, 25–26 August 2016, Paper No 26. New York: ACM.Google Scholar
- Shah, N., & Mahajan, S. (2014). Distributed document clustering using K-means. International Journal of Advanced Research in Computer Science and Software Engineering, 4, 24–29.Google Scholar
- Tadano, R., Shimada, K., & Endo, T. (2010). Multi-aspects review summarization based on identification of important opinions and their similarity. In 24th Pacific Asia conference on language, information and computation (PACLIC), Sendai, Japan, 4–7 November 2010 (pp. 685–692). Sendai, Japan: Institute for Digital Enhancement of Cognitive Development.Google Scholar
- Umamaheswari, K., & Priya, V. (2016). Aspect ranking based on author specific information aggregation. Journal of Scientific and Industrial Research, 75, 534–539.Google Scholar
- Woo-Hyun Lee, Hee-Gook Jun, & Hyoung-Joo Kim. (2015). Hadoop Mapreduce performance enhancement using in-node combiners. International Journal of Computer Science & Information Technology, 7(5), 1–17.Google Scholar
- Zhao Weizhong, Ma Huifang, & He Qing. (2009). Parallel K-means clustering based on MapReduce. In First international conference on CloudCom 2009, Beijing, China, 1–4 December 2009, Paper no. LNCS 5931 (pp. 674–679). Heidelberg: Springer.Google Scholar
- Zhuang, L., Jing, F., & Zhu, X. (2006). Movie review mining and summarization. In International Conference on Information and Knowledge Management (CIKM), Arlington, VA, USA, 5–11 November 2006 (pp. 43–50). New York: ACM.Google Scholar