Comparing consumer-produced product reviews across multiple websites with sentiment classification

ABSTRACT

Online consumer reviews have been extensively studied. However, existing literature analyzing online consumer review data mostly relies on a single data source, resulting in potentially biased analytics conclusions. Many websites encourage consumers to post reviews of their purchased products, so that new consumers can evaluate these reviews for the same product across different websites to help them make purchasing decisions. Confusions often arise in this process, because there often exist substantial discrepancies in customer reviews across different retailers on the same product. Clarifying such confusions can help consumers reduce concerns to make up their mind for their purchases, therefore benefiting both consumers and retailers. Through text analytics and sentiment analysis, we comparatively examine the underlying patterns of online consumer reviews of three large retailers including Sears, Home Depot, and Best Buy for a same product. Afterward, we combine online consumer reviews from these large retailers and conduct an overall text analytics and sentiment analysis. The overall results are further compared with the results from individual retailers. The findings show that the sentiment of the online consumer reviews could vary substantially so relying on a single data source to make purchase decision is not a wise idea. Based on the results, we further devise a framework to comparatively examine and integrate multiple data sources for social media analytics of online consumer reviews. This study offers important managerial implications and identifies several new research directions for social media analytics.     

Green consumer market segmentation: empirical findings from Portugal

Concern with environmental degradation has led to a new segment of consumers: the green or ecological consumers. Marketers must pay special attention to the needs of this segment. The growing concern with the environment, increased competition and greater selectiveness and demands of consumers represent an immediate challenge for green marketing. This paper aims to identify distinct market segments based on several environmental variables. It also investigates individuals' behaviours and perceptions about green consumerism. The used methodology was the collection of primary information through a direct survey. The study covered 887 Portuguese consumers, aged over 18. The results show that certain environmental and demographic variables are significant in differentiating between the ‘greener’ consumer group and the other segments. Portuguese consumers, despite their support for policies designed to improve the environment, do not always translate their concerns into environmentally friendly actions. Possible implications of these results for firms' marketing strategies are also discussed.     

‘We (don’t) know how you feel’ – a comparative study of automated vs. manual analysis of social media conversations

Abstract

The ever-growing volume of brand-related conversations on social media platforms has captivated the attention of academics and practitioners, as the analysis of those conversations promises to offer unparalleled insight into consumers’ emotions. This article takes a step back from the hype, and investigates the vulnerabilities related to the analysis of social media data concerning consumers’ sentiment. A review of the literature indicates that the form, focus, source and context of the communication may negatively impact on the analyst’s ability to identify sentiment polarity and emotional state. Likewise, the selection of analytical tool, the creation of codes, and the classification of the data, adversely affect the researcher’s ability to accurately assess the sentiment expressed in a social media conversation. Our study of Twitter conversations about coffee shows low levels of agreement between manual and automated analysis, which is of grave concern given the popularity of the latter in consumer research.     

Consumer socialization,social structural factors and decision‐making styles: a case study of adolescents in Malaysia

The purpose of this study is to investigate how the process of consumer socialization will determine adolescents’ decision‐making styles. Eight decision‐making styles were conceptualized as outcomes of the socialization process, which is acquired via interaction with socialization agents, namely parents, peers, printed media, television commercials and in‐school education. The study also proposed five social structural variables (social class, gender, ethnicity, residence and religion) as being associated with the socialization agents and decision‐making styles. The study sample consisted of 934 adolescents between the ages of 16 and 19 years. The data were collected using a self‐administered questionnaire and analysed with the SPSS computer program. As a result of regression analyses, significant relationships were found between social structural factors and socialization processes, suggesting that the influence of socialization agents on adolescents may vary according to certain demographic characteristics. Significant relationships were also found between social structural factors and socialization processes. Peers appeared to be the most important agents of consumer socialization, contributing to a variety of desirable as well as undesirable consumer decision styles. Printed media and television commercials were also found to be significant sources of the acquisition of both desirable and undesirable decision‐making styles. Parents and in‐school education, however, were insignificant in the acquisition of any decision‐making styles among adolescents. Information obtained from this study could be useful to government agencies and consumer educators. The most revealing finding of this study is that parents did not contribute to the formulation of decision‐making orientation for adolescents. This points to the need for consumer educators to take steps in designing programmes that will involve parents as primary socialization agents at home; this may be facilitated via printed materials. Apart from this, the information can also be helpful in enabling marketers to be more effective in targeting various adolescent markets by formulating marketing strategies according to demographic factors, socialization process and decision‐making styles.     

How does perception on green environment across generations affect consumer behaviour? A neural network process

This paper examines how the perception on green environment can affect consumer behaviour. It tests whether consumer behaviour responds to environmental change. This study captures the interaction between green environment perception and behaviour. A neural network analysis is used to address this challenge to model such a behaviour. A total of 462 interviews were conducted and analysed using neural network process. A Scaled Conjugate Gradient with random data division was used in training and the performance was calculated using mean square error. The result reveals that perception–behaviour gap exists across generations on green environment. It indicates that perception on green producing, green living, green transport and green product is an important factor in determining the behaviour on green consumption. The neural network accurately recognized green behaviour up to nearly 82% with MSE = 0.09 at epoch 31, which is a high level of recognition accuracy. This study underlines the existence of perception–behaviour gap on green environment. However, these are only identified to people with low‐to‐medium level of green behaviours (level of correct only 44.5% and 30%). People with high level of green behaviour in fact show consistency between their perceptions and behaviours (level of correct 96.4%). This result shows that people tend to have higher perceptions on green environment, but their behaviour reflects otherwise.     

A content analysis of male roles in television advertising: Do traditional roles still hold?

Analysis of male roles in television advertising is limited. In order to remedy this, our research serves as a catalyst by providing a review of the current literature, conducting a preliminary examination of male roles in television advertising, and discussing ways for this area of research to move forward in the future. Specifically, the study conducted in this paper examines television advertising to provide insight on the depiction of males, the portrayed relations between males and other individuals, and how these depictions may have changed from 2003 to 2008. Male depictions in lead roles are contrasted using 907 primetime commercials from 2003 and 961 commercials from 2008 from the four major US broadcasting networks (ABC, NBC, CBS, and FOX). Results suggest that some aspects of male depictions in advertising are counter to, while other aspects are reflective of, the changing gender roles occurring in society.