0
Research Papers

Quantifying Product Favorability and Extracting Notable Product Features Using Large Scale Social Media Data

[+] Author and Article Information
Suppawong Tuarob

Computer Science and Engineering,
Industrial and Manufacturing Engineering,
The Pennsylvania State University,
University Park, PA 16802
e-mail: suppawong@psu.edu

Conrad S. Tucker

Engineering Design and Industrial Engineering,
Computer Science and Engineering,
The Pennsylvania State University,
University Park, PA 16802
e-mail: ctucker4@psu.edu

Contributed by the Computers and Information Division of ASME for publication in the JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING. Manuscript received June 20, 2014; final manuscript received December 11, 2014; published online April 9, 2015. Assoc. Editor: Joshua D. Summers.

J. Comput. Inf. Sci. Eng 15(3), 031003 (Sep 01, 2015) (12 pages) Paper No: JCISE-14-1216; doi: 10.1115/1.4029562 History: Received June 20, 2014; Revised December 11, 2014; Online April 09, 2015

Some of the challenges that designers face in getting broad external input from customers during and after product launch include geographic limitations and the need for physical interaction with the design artifact(s). Having to conduct such user-based studies would require huge amounts of time and financial resources. In the past decade, social media has emerged as an increasingly important medium of communication and information sharing. Being able to mine and harness product-relevant knowledge within such a massive, readily accessible collection of data would give designers an alternative way to learn customers' preferences in a timely and cost-effective manner. In this paper, we propose a data mining driven methodology that identifies product features and associated customer opinions favorably received in the market space which can then be integrated into the design of next generation products. Two unique product domains (smartphones and automobiles) are investigated to validate the proposed methodology and establish social media data as a viable source of large scale, heterogeneous data relevant to next generation product design and development. We demonstrate in our case studies that incorporating suggested features into next generation products can result in favorable sentiment from social media users.

FIGURES IN THIS ARTICLE
<>
Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Proposed method for quantifying PF and product features

Grahic Jump Location
Fig. 3

Comparison between the Favorability score versus U.S. News and consumer reports ratings for each sample automobile model. The models are ordered by their Favorability scores.

Grahic Jump Location
Fig. 2

Comparison between the PF score versus GSMArea daily interest for each sample smartphone model (in log scale). The products are ordered by their Favorability scores.

Grahic Jump Location
Fig. 5

Comparison between the positive and negative sentiments related to some features of Samsung Galaxy S II and Samsung Galaxy S III

Grahic Jump Location
Fig. 4

Comparison between the positive and negative sentiments related to some features of iPhone 4 and iPhone 5

Grahic Jump Location
Fig. 6

Sample feature opinions related to the iPhone 4, arranged in hierarchy of Product Name → Feature → Opinion → Snippets

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In