IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 8 - Issue 10, October 2019 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Summarizing Product Reviews Using NLP Based Text Summarization

[Full Text]

 

AUTHOR(S)

Ravali Boorugu, Dr. Gajula Ramesh, Dr. Karanam Madhavi

 

KEYWORDS

Attention Mechanism, Conceptnet Numberbatch, LSTM, NLP Techniques, Product Review, Seq2Seq Model, Text Summarization

 

ABSTRACT

Shopping was confined just to outdoor shopping few years ago when there were no websites for online shopping and no internet. But now Internet is available to everyone at fingertips with the advent of smartphones, tablets, laptops and even the cheaper rate to afford internet. This was the prime reason for the sudden booming of online shopping websites. Nowadays everyone loves online shopping. Everyone wishes to order products rather than buying directly from the shops. The primary thing a person will check before ordering the product is a review given by the customers who bought it already. It is becoming difficult for a user to go through various reviews of different products of a particular type and choose the best among them. Thus the need arises for the summarization of these reviews to the maximum extent possible, in order to make the user choose the best product from the whole lot. The process of minimizing the content of a given document without any loss in the meaning of the content is called as Text Summarization. It is grabbing attention of many NLP Researchers nowadays. Text Summarization is categorized based on Input type, Output type and Purpose. We will discuss in brief the various types of text summarization in detail in this paper. We propose seq2seq model for summarization. Its advanced version i.e LSTM is used along with the attention mechanism for increased accuracy. We used the latest word embedding model Conceptnet Numberbatch which is very much similar to GloVe but comparatively better than that. During classification we use 1D convolutional layer followed by max pooling layer, LSTM layer and then at the end by a fully connected layer.

 

REFERENCES

[1] Shi Ziyan “The Design and Implementation of Domain-specific Text Summarization System based on Co-reference Resolution Algorithm” 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.
[2] Niladri Chatterjee, Amol Mittal and Shubham Goyal’s “Single Document Extractive Text Summarization Using Genetic Algorithms” (2012)
[3] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean,” Distributed Representations of Words and Phrases and their Compositionality,” arXiv:1310.4546v1 [cs.CL], 2013
[4] Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean, "Efficient Estimation of Word Representations in Vector Space," arXiv:1301.3781v3 [cs.CL], 2013.
[5] Amol Tandel, Brijesh Modi, Priyasha Gupta, Shreya Wagle and Sujata Khedkar's "Multi-document text summarization - A survey" 2016 International Conference on Data Mining and Advanced Computing (SAPIENCE)
[6] Aditya Jain, Divij Bhatia, Manish K Thakur’s “Extractive Text Summarization using Word Vector Embedding”(2017).
[7] Yang Wei and Yang Zhizhuo “Query based Summarization using topic background knowledge” 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)
[8] Priya Pawar, Siddhesha Tandel, Shweta Bore & Nikita Patil “Online Product Review Summarization” 2017 International Conference on Innovations in Information, Embedded andCommunication Systems (ICIIEC
[9] Paul Gigioli, Nikhita Sagar, Anand Rao, Joseph Voyles “Domain-Aware Abstractive Text Summarization for Medical Documents” published during 2018 IEEE BIBM.
[10] Shivangi Modi & Rachana Oza “Review on Abstractive Text Summarization Techniques (ATST) for single and multi documents” 2018 International Conference on Computing, Power and Communication Technologies.
[11] Nithin Raphal, Hemanta Duwarah and Philemon Daniel “Survey on Abstractive Text Summarization” 2018 International Conference on Communication and Signal Processing (ICCSP).