Identifying comparative customer requirements from product online reviews for competitor analysis

Jin, Jian; Ji, Ping; Gu, Rui

doi:10.1016/j.engappai.2015.12.005

Cited by 136 publications

(77 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Works which is described in [13,15,16] are di®erent than proposed work which described in this paper in such a way that, in proposed work authors extract valuemeasure pairs given their attributes and data types. The authors also execute the extraction process on product description pages of di®erent retailers.…”

Section: Product Class Name: Electric Timermentioning

confidence: 83%

See 1 more Smart Citation

Comparative Search of Entities

Thakare

Deshpande

2017

Int. J. Soft. Eng. Knowl. Eng.

View full text Add to dashboard Cite

Nowadays, every manufacturer or retailer displays their product information on various websites. The customer has to visit, the number of such web pages to choose the right product, because the information is not available at one place. There are some websites that show such information in one place, but they are product speci¯c and in general information is manually updated. In this paper, we propose a novel concept of web-spreadsheet, which displays product information by crawling through related web pages and generates information like a spreadsheet where each row represents product information and each column represents product attributes. We are extracting the product name of speci¯ed product class using decision tree-based classi¯er by features obtained using Part of Speech (POS) tagging and distance measure. It also extracts the value-measure pairs of preset attributes using distance measure, POS tagging and Data type. This approach will save a lot of time of comparing di®erent products and customers need not have to scan a number of websites for comparison. We present promising results in various product classes which surpass many existing techniques in the literature. The proposed method can work accurately without initial trained labeled data which is expensive to obtain.

show abstract

Section: Product Class Name: Electric Timermentioning

confidence: 83%

“…Recent work on extracting pairs of comparative sentences from online reviews of products has been discussed [13]. In this work, features are extracted from pros and cons sentences of the customer views of the product.…”

Section: Related Workmentioning

confidence: 99%

Comparative Search of Entities

Thakare

Deshpande

2017

Int. J. Soft. Eng. Knowl. Eng.

View full text Add to dashboard Cite

show abstract

“…Our work is different than the work described in [22][23][24] in such a way that, in the work which is described in this paper we automatically extract attribute-value pairs. We perform the extraction process on different product description pages of various retailers or manufacturers.…”

Section: Product Class Name: Electric Timermentioning

confidence: 84%

“…In the work done by [22], features are extracted from the pros and cons sentences of the customer views of the product. For extracting product features and opinions from reviews, [23] calculate point of mutual information between the nounphrases and related context patterns.…”

Section: Related Workmentioning

confidence: 99%

Automatic Extraction of Attributes and Entities for Product Differentiation

Thakare¹,

Deshpande²

2018

IJCIS

View full text Add to dashboard Cite

This paper introduces a novel concept of web-spreadsheet, which extracts product information by crawling through related web pages and generates information like a spreadsheet where each row represents product information and each column represents product attributes. Using Decision Tree based classifier, the accuracy achieved for extracting entities and attribute-value pairs is 98.71% and 99.99% respectively. This strategy will benefit the product companies for performing successful product differentiation and save a lot of time of the customers for comparing different products of same product class.

show abstract

“…The only work we could identify that considers competitors (see Sect. 2) extracts and compares pairs of sentences for the same feature from multiple reviews [16].…”

Section: Introductionmentioning

confidence: 99%

RE-SWOT: From User Feedback to Requirements via Competitor Analysis

Dalpiaz

Parente²

2019

Requirements Engineering: Foundation for Software Quality

View full text Add to dashboard Cite

Context & Motivation] App store reviews are a rich source for analysts to elicit requirements from user feedback, for they describe bugs to be fixed, requested features, and possible improvements. Product development teams need new techniques that help them make real-time decisions based on user feedback. [Question/Problem] Researchers have proposed natural language processing (NLP) techniques for extracting and organizing requirements-relevant knowledge from the reviews for one specific app. However, no attention has been paid to studying whether and how requirements can be identified from competing products. [Principal ideas/results] We propose RE-SWOT, a tool-supported method for eliciting requirements from app store reviews through competitor analysis. RE-SWOT combines NLP algorithms with information visualization techniques. We evaluate the usefulness of RE-SWOT with expert product managers from three mobile app companies.[Contribution] Our preliminary results show that competitor analysis is a promising path for research that has direct impact on the requirements engineering practice in modern app development companies.

show abstract

Identifying comparative customer requirements from product online reviews for competitor analysis

Cited by 136 publications

References 35 publications

Comparative Search of Entities

Comparative Search of Entities

Automatic Extraction of Attributes and Entities for Product Differentiation

RE-SWOT: From User Feedback to Requirements via Competitor Analysis

Contact Info

Product

Resources

About