E-commerce Product’s Trust Prediction Based on Customer Reviews

Hrutuja Kargirwar; Praveen Bhagavatula; Shrutika Konde; Paresh Chaudhari; Vipul  Dhamde; Gopal  Sakarkar; Juan C Correa

doi:10.1007/978-981-19-9225-4_28

E-commerce Product’s Trust Prediction Based on Customer Reviews

Hrutuja Kargirwar, Praveen Bhagavatula^*, Shrutika Konde, Paresh Chaudhari, Vipul Dhamde, Gopal Sakarkar, Juan C Correa

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

The Internet is strengthening the e-commerce industry, which is fast growing and helping enterprises of all sizes, from multinational organizations to tiny firms. Customers may buy things online with little or no personal interaction with sellers they purchase online; user reviews play a vital role in online shopping. Consumers’ comprehension and interpretation of product reviews impacts buying decisions. This research paperwork presents a unique, reproducible data processing methodology for customer evaluations across 10 product categories on India’s one of the most popular e-commerce platforms with 11,559 customer reviews. We investigated the efficacy of a collection of machine learning algorithms that may be used to assess huge reviews on e-commerce platforms by using consumer ratings as a source to automatically classify product reviews as highly trustable or not-so-trustable. Results show that the algorithms can reach up to 85% of accuracy in classifying product reviews correctly. The research discusses the practical ramifications of these findings in terms of consumer complaints and product returns, as evidenced by customer reviews.

Original language	English
Title of host publication	3rd Congress on Intelligent Systems - Proceedings of CIS 2022
Editors	Sandeep Kumar, Harish Sharma, K. Balachandran, Joong Hoon Kim, Jagdish Chand Bansal
Publisher	Springer Nature
Pages	375-383
Number of pages	9
Volume	1
ISBN (Electronic)	978-981-19-9225-4
ISBN (Print)	978-981-19-9224-7
DOIs	https://doi.org/10.1007/978-981-19-9225-4_28
Publication status	Published - 2023
Externally published	Yes

Publication series

Name	Lecture Notes in Networks and Systems
Volume	608
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Access to Document

10.1007/978-981-19-9225-4_28

Cite this

Kargirwar, H., Bhagavatula, P., Konde, S., Chaudhari, P., Dhamde, V., Sakarkar, G., & Correa, J. C. (2023). E-commerce Product’s Trust Prediction Based on Customer Reviews. In S. Kumar, H. Sharma, K. Balachandran, J. H. Kim, & J. C. Bansal (Eds.), 3rd Congress on Intelligent Systems - Proceedings of CIS 2022 (Vol. 1, pp. 375-383). (Lecture Notes in Networks and Systems; Vol. 608). Springer Nature. https://doi.org/10.1007/978-981-19-9225-4_28

Kargirwar, Hrutuja ; Bhagavatula, Praveen ; Konde, Shrutika et al. / E-commerce Product’s Trust Prediction Based on Customer Reviews. 3rd Congress on Intelligent Systems - Proceedings of CIS 2022. editor / Sandeep Kumar ; Harish Sharma ; K. Balachandran ; Joong Hoon Kim ; Jagdish Chand Bansal. Vol. 1 Springer Nature, 2023. pp. 375-383 (Lecture Notes in Networks and Systems).

@inproceedings{6d748f253b8a4aa5aaaa37ef1eb6bf9c,

title = "E-commerce Product{\textquoteright}s Trust Prediction Based on Customer Reviews",

abstract = "The Internet is strengthening the e-commerce industry, which is fast growing and helping enterprises of all sizes, from multinational organizations to tiny firms. Customers may buy things online with little or no personal interaction with sellers they purchase online; user reviews play a vital role in online shopping. Consumers{\textquoteright} comprehension and interpretation of product reviews impacts buying decisions. This research paperwork presents a unique, reproducible data processing methodology for customer evaluations across 10 product categories on India{\textquoteright}s one of the most popular e-commerce platforms with 11,559 customer reviews. We investigated the efficacy of a collection of machine learning algorithms that may be used to assess huge reviews on e-commerce platforms by using consumer ratings as a source to automatically classify product reviews as highly trustable or not-so-trustable. Results show that the algorithms can reach up to 85% of accuracy in classifying product reviews correctly. The research discusses the practical ramifications of these findings in terms of consumer complaints and product returns, as evidenced by customer reviews.",

author = "Hrutuja Kargirwar and Praveen Bhagavatula and Shrutika Konde and Paresh Chaudhari and Vipul Dhamde and Gopal Sakarkar and Correa, {Juan C}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.",

year = "2023",

doi = "10.1007/978-981-19-9225-4_28",

language = "English",

isbn = "978-981-19-9224-7",

volume = "1",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Nature",

pages = "375--383",

editor = "Kumar, {Sandeep } and Sharma, {Harish } and K. Balachandran and Kim, {Joong Hoon } and Bansal, {Jagdish Chand }",

booktitle = "3rd Congress on Intelligent Systems - Proceedings of CIS 2022",

address = "Singapore",

}

Kargirwar, H, Bhagavatula, P, Konde, S, Chaudhari, P, Dhamde, V, Sakarkar, G & Correa, JC 2023, E-commerce Product’s Trust Prediction Based on Customer Reviews. in S Kumar, H Sharma, K Balachandran, JH Kim & JC Bansal (eds), 3rd Congress on Intelligent Systems - Proceedings of CIS 2022. vol. 1, Lecture Notes in Networks and Systems, vol. 608, Springer Nature, pp. 375-383. https://doi.org/10.1007/978-981-19-9225-4_28

E-commerce Product’s Trust Prediction Based on Customer Reviews. / Kargirwar, Hrutuja; Bhagavatula, Praveen; Konde, Shrutika et al.
3rd Congress on Intelligent Systems - Proceedings of CIS 2022. ed. / Sandeep Kumar; Harish Sharma; K. Balachandran; Joong Hoon Kim; Jagdish Chand Bansal. Vol. 1 Springer Nature, 2023. p. 375-383 (Lecture Notes in Networks and Systems; Vol. 608).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - E-commerce Product’s Trust Prediction Based on Customer Reviews

AU - Kargirwar, Hrutuja

AU - Bhagavatula, Praveen

AU - Konde, Shrutika

AU - Chaudhari, Paresh

AU - Dhamde, Vipul

AU - Sakarkar, Gopal

AU - Correa, Juan C

PY - 2023

Y1 - 2023

N2 - The Internet is strengthening the e-commerce industry, which is fast growing and helping enterprises of all sizes, from multinational organizations to tiny firms. Customers may buy things online with little or no personal interaction with sellers they purchase online; user reviews play a vital role in online shopping. Consumers’ comprehension and interpretation of product reviews impacts buying decisions. This research paperwork presents a unique, reproducible data processing methodology for customer evaluations across 10 product categories on India’s one of the most popular e-commerce platforms with 11,559 customer reviews. We investigated the efficacy of a collection of machine learning algorithms that may be used to assess huge reviews on e-commerce platforms by using consumer ratings as a source to automatically classify product reviews as highly trustable or not-so-trustable. Results show that the algorithms can reach up to 85% of accuracy in classifying product reviews correctly. The research discusses the practical ramifications of these findings in terms of consumer complaints and product returns, as evidenced by customer reviews.

AB - The Internet is strengthening the e-commerce industry, which is fast growing and helping enterprises of all sizes, from multinational organizations to tiny firms. Customers may buy things online with little or no personal interaction with sellers they purchase online; user reviews play a vital role in online shopping. Consumers’ comprehension and interpretation of product reviews impacts buying decisions. This research paperwork presents a unique, reproducible data processing methodology for customer evaluations across 10 product categories on India’s one of the most popular e-commerce platforms with 11,559 customer reviews. We investigated the efficacy of a collection of machine learning algorithms that may be used to assess huge reviews on e-commerce platforms by using consumer ratings as a source to automatically classify product reviews as highly trustable or not-so-trustable. Results show that the algorithms can reach up to 85% of accuracy in classifying product reviews correctly. The research discusses the practical ramifications of these findings in terms of consumer complaints and product returns, as evidenced by customer reviews.

UR - http://www.scopus.com/inward/record.url?scp=85150982506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85150982506&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-9225-4_28

DO - 10.1007/978-981-19-9225-4_28

M3 - Conference contribution

SN - 978-981-19-9224-7

VL - 1

T3 - Lecture Notes in Networks and Systems

SP - 375

EP - 383

BT - 3rd Congress on Intelligent Systems - Proceedings of CIS 2022

A2 - Kumar, Sandeep

A2 - Sharma, Harish

A2 - Balachandran, K.

A2 - Kim, Joong Hoon

A2 - Bansal, Jagdish Chand

PB - Springer Nature

ER -

Kargirwar H, Bhagavatula P, Konde S, Chaudhari P, Dhamde V, Sakarkar G et al. E-commerce Product’s Trust Prediction Based on Customer Reviews. In Kumar S, Sharma H, Balachandran K, Kim JH, Bansal JC, editors, 3rd Congress on Intelligent Systems - Proceedings of CIS 2022. Vol. 1. Springer Nature. 2023. p. 375-383. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-19-9225-4_28

E-commerce Product’s Trust Prediction Based on Customer Reviews

Abstract

Publication series

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this