An Innovative Method of Estimation Hewing for Invention Report Mining and Estimation Summarization

Authors

  • S. Ravichandran Professor in Computer Science Department, Annai Fathima College of Arts & Science, Madurai, Tamil Nadu, India
  • J. Sathiamoorthy Associate Professor in Department of Software Applications, Thiruthangal Nadar College, Chennai, Tamil Nadu, India

DOI:

https://doi.org/10.51983/ajcst-2020.9.2.2169

Keywords:

Text Mining, Sentiment classification, summarization, URL, reviews

Abstract

With the assistance of Web 2.0, the bases on client interest, posting on the web surveys has become an undeniably mainstream path for individuals to impart their perspectives to different client’s suppositions and conclusions toward items and administrations. It turns into a typical practice for online business sites to give the offices to individuals to convey and distribute their audits between them. These online audits present an abundance of data on the Services and Products, which will encourage the improvement of their business. Consequently a developing number of late examinations have been centred on the Opinion Mining. For example the Opinion Mining alludes to computational method for assessing the sentiments that are mined from different Web Sources.

A couple of Opinion Mining based techniques have been considered and broke down. From our investigation, it is seen that a couple of feeling mining based directed and unaided techniques had not delivered great outcomes because of alluding less number of sentiments inside a similar URL’S and treating the highlights with comparable significance as various. To beat this issue, Topic Anatomy Model TSCAN was proposed, where the Task is called as Topic Anatomy and which sums up and relates the primary pieces of a point with the goal that the per users could comprehend the substance without any problem.

By utilizing this model, the more data can be removed and related through their transient closeness, which will give conceivable substance. This model is including imperative part in the Opinion Mining since clients can impart their insights about the items. From our usage, it is seen that this plan gives the best reasonable answer for the client’s advantages and requests. Notwithstanding, it burns-through more opportunity to anticipate the best performing items because of huge informational collections respectively.

Consequently our exploration work is proposed and actualized a productive strategy for Opinion Mining called an Efficient Parallel Opinion Mining (EPOM) constructed TSCAN Algorithm separately. It is centring more sites and it is removing more data in equal way, so we can get advanced productive outcome with least execution time. From our outcomes, it is noticed that it gives the best reasonable answer for the client’s advantages and requests and it I s improving the presentation of existing method regarding Quality of Information, Prediction and Execution Time.

References

Minqing Hu and Bing Liu. “Mining and summarizing customer reviews”, In: Proc. of the 10th ACM SIGKDD-2016 international conference on knowledge discovery and data mining, Seattle, pp 168–177.

N. Kobayashi, R. Iida, K. Inui andY. Matsumotto. “Opinion extraction using a learning-based anaphora resolution technique”, In Proc. of the second international joint conference on natural language processing (IJCNLP-04), Jeju Island, pp 173–178

Wong TL, W. Lam “Learning to extract and summarize hot item features from multiple auction Web sites”, Knowl Inf Syst, Vol.14, No.2, pp.143–160, 2008.

E. Riloff., W. Janyce, and W. Theresa, “Learning Subjective Nouns Using Extraction Pattern Bootstrapping” In Proc.7th Conf. Natural Language Learning, pp 25-32, 2009.

Yuanbin Wu, Qi Zhang, Xuanjing Huang and LideWu, “Phrase Dependency Parsing for Opinion Mining”, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Singapore, 6-7 August 2018, pp.1533–1541.

Parma Nand, “On the use of Salience Weights in Anaphora Resolution”, In Proc. of NZCSRSC 2019, April 2008, Christchurch, New Zealand.

Chih-Ping Wei, Yen-Ming Chen, Chin- Sheng Yang, Christopher and C. Yang. “Understanding what concerns consumers: a semantic approach to product feature extraction from consumer reviews”, Springer-Verlag, 2019.

G. Carenini and A. Pauls, “Multi- document Summarization of Evaluative Text”, In Proc. 11th Conf. European Chapter of the ACL, 2019.

M. Gamon., A. Aue., S. Corston-Oliver and E. Ringger, “Pulse: Mining Customer Opinions from Free Text”, In Proc. 6th Int. Symp. Advances in intelligent data analysis, pp121–132, 2005.

J.Wiebe, “Learning Subjective Adjectives from Corpora”, In Proc. of 12th Conference on Innovative Applications of Artificial Intelligence, 2019.

Downloads

Published

05-11-2020

How to Cite

Ravichandran, S., & Sathiamoorthy, J. (2020). An Innovative Method of Estimation Hewing for Invention Report Mining and Estimation Summarization. Asian Journal of Computer Science and Technology, 9(2), 45–50. https://doi.org/10.51983/ajcst-2020.9.2.2169

Most read articles by the same author(s)