Dynamic perceived quality analysis using social media data at macro- and micro-levels
| DOI | https://doi.org/10.1108/IMDS-08-2022-0478 |
| Published date | 21 March 2023 |
| Date | 21 March 2023 |
| Pages | 1465-1495 |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
| Author | Tong Yang,Yanzhong Dang,Jiangning Wu |
Dynamic perceived quality
analysis using social media data
at macro- and micro-levels
Tong Yang, Yanzhong Dang and Jiangning Wu
Institute of Systems Engineering, Dalian University of Technology, Dalian, China
Abstract
Purpose –This paper aims to propose a method for dynamic product perceived quality analysis using social
media data and to achieve a macro–micro combination analysis. The method enables the prioritization of
perceived quality attributes and provides perception causes.
Design/methodology/approach –To rationalize the macro–micro combination, ANOVA and multiple
linear regression were used to identify the main factors affecting perceived quality which served as the
combination basis; by using the combination basis for consumer segmentation, macro-knowledge (i.e. attribute
importance and quality category of the attribute) is achieved by term frequency-inverse document frequency
(TF-IDF)-based attribute importance calculation and KANO-based attribute classification, which is combined
with micro-quality diagnostic information (i.e. perceived quality, perception causes and quality parameters).
Further, dynamic perception Importance-Performance Analysis (IPA) is built to present the attribute priority
and perception causes.
Findings –The framework was validated by the new energy vehicle (NEV) data of Autohome. The results
show that price and purchase purpose are the most influential factors of perceived quality and that dynamic
perception IPA can effectively prioritize attributes and mine perception causes.
Originality/value –This is one of the first studies to analyze dynamic perceived quality using social media
data, which contributes to the research on perceived quality. The paper also contributes by achieving a
combined macro–micro analysis of perceived quality. The method rationalizes the macro–micro combination
by identifying the factors influencing perceived quality, which provides ideas for other studies using social
media data.
Keywords Dynamic perceived quality, Macro–micro combination, Social media data, Attribute prioritization,
Perception causes
Paper type Research paper
1. Introduction
Manufacturers are faced with the challenge of constantly updating their products and
improvingquality.Perceived quality,which is generatedby consumersduring use (Golder et al.,
2012;Mitra and Golder, 2006), has a significant impact on consumers’purchasing decisions
(Wang et al., 2018;Xu et al., 2019). High perceived quality means products are favored by
consumers, so perceived quality has significance for manufacturers to establish a competitive
advantage (Akdeniz and Calantone, 2017). With the development of social media, increasing
Dynamic
perceived
quality
analysis
1465
The authors acknowledge the Center for Big Data and Intelligent Decision-Making of the Dalian
University of Technology for providing computing resources.
Funding: This work was supported by the National Natural Science Foundation of China [project
numbers 71871041], and China Scholarship Council [202106060118].
Geolocation information: This work was carried out at the Dalian University of Technology (38.
8847N, 121.5197E).
Data availability statement: Data available on reasonable request from the authors.
Declaration of interest statement: There is no conflict of interest in the manuscript which is approved
by all authors for publication. The authors would like to declare that all or part of the work described in
the manuscript is original research, which has not been published elsewhere and is not prepared for
publication elsewhere.
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/0263-5577.htm
Received 9 August 2022
Revised 8 November 2022
7 January 2023
Accepted 9 February 2023
Industrial Management & Data
Systems
Vol. 123 No. 5, 2023
pp. 1465-1495
© Emerald Publishing Limited
0263-5577
DOI 10.1108/IMDS-08-2022-0478
consumers are sharing their product quality perceptions online (He et al., 2018;Zheng et al., 2020).
Simultaneously, a growingnumber of consumers are referring to information from reviewson
social media before making a purchase (Wu and Zhao, 2022). Such social media data generated
by consumers are comprehensive, authentic and easily accessible (Bi et al., 2019;Chan et al.,
2015), providing opportunities for reliable perceived quality analysis.
As a consumer-centric approach to product development, research into perceived quality
using social media data continues to grow, especially its quantification methods (He et al.,
2018;Zheng et al., 2020). For instance, He et al. (2018) proposed a fuzzy-combined text mining
method to evaluate the multi-attribute perceived quality of mobile phones using reviews.
Given that perceived quality is subjective and constantly changing (Mitra and Golder, 2006;
Slotegraaf and Inman, 2004), quantifying this pattern of change is important for research into
the quantification of perceived quality as it helps reveal and understand the evolutionary
path of consumer perception. Meanwhile, capturing the changing trends can help
manufacturers understand the evolving patterns of perceived quality (Mitra and Golder,
2006;Slotegraaf and Inman, 2004) and thus better improve product quality based on
consumer perceptions. Nevertheless, the existing methods for quantifying perceived quality
are mainly conducted from a static perspective.
Moreover, it is necessary for a perceived quality quantification method to deal with both
macro-level and micro-level information, which enables the measurement of overall market
acceptance and the diagnosis of specific quality (Hsiao and Hsiao, 2021). However, existing
research on perceived quality using social media data has been conducted either at the macro-
level (e.g. Yoon et al., 2020;Golara et al., 2021) or at the micro-level (e.g. Liu et al., 2018;Zheng
et al., 2021), with few studies conducting a combination of macro–micro analysis. The macro-
level analysis provides aggregated and non-discriminatory knowledge that can be applied as
a guideline for developing and managing quality, but cannot indicate weakness for the
individual product (Hsiao and Hsiao, 2021;Schivinski et al., 2019). Nevertheless, micro-level
studies provide manufacturers with specific quality diagnoses, but ignore the role of the
holistic market and the results would be difficult to scale (Schivinski et al., 2019).
Social media data provides ample macro- and micro-information for research on the
quantification of perceived quality. Compared to questionnaire data, social media data is
more rapidly updated, which makes dynamic methods of quantifying perceived quality
important. This research aims to expand research on perceived quality quantification by
constructing a dynamic analysis method of perceived quality through social media data,
which enables a combined analysis of macro- and micro-information. In the process, this
study attempts to answer the following questions:
RQ1. How to capture dynamic product perceived quality from social media data?
RQ2. How to develop quality improvement strategies from a macro–micro
combined view?
Focusing on these questions, we propose an innovative 2-stageframework withmixed methods
using social media data. Micro-level product quality diagnostic information is used to identify
the product’s strengths and weaknesses, which needs to be combined with macro-level market
knowledge. In this process, finding appropriate macro-knowledge is key to the effectiveness of
the combination. Because perceived quality is a subjective feeling that varies between
individuals (Mitraand Golder, 2006), different consumer groups show varying perceived quality.
Therefore, a rational consumer segmentation allows for a more effective macro–micro
combination analysis. Consequently, we first clarify the main factors influencing the product’s
perceived quality in Stage 1, using them to segment consumers. Specifically, ANOVA is
conducted to identify product-level factors; and attribute-level factors are further analyzed
through multiple linear regression. In addition, producing products with high perceived quality
IMDS
123,5
1466
To continue reading
Request your trial