Mass-scale emotionality reveals human behaviour and marketplace success

Rocklage, Matthew D.; Rucker, Derek D.; Nordgren, Loran F.

doi:10.1038/s41562-021-01098-5

Cited by 35 publications

(41 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have found that in contrast to online ratings, potential consumers often refer to reviews from other customers who have already spent money making purchase decisions (Kwon et al , 2021). Among other things, the emotion in the text may be more indicative of the success of the product or service (Rocklage et al , 2021). Moreover, in emotional psychology, there are different types of emotions, which are discrete (Izard and Carroll, 1977; Plutchik, 2000).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

What affects the online ratings of restaurant consumers: a research perspective on text-mining big data analysis

Mehraliyev

et al. 2022

IJCHM

View full text Add to dashboard Cite

Purpose Despite a significant focus on customer evaluation and sentiment analysis, limited attention has been paid to discrete emotional perspective in terms of the emotionality used in text. This paper aims to extend the general-sentiment dictionary in Chinese to a restaurant-domain-specific dictionary, visualize spatiotemporal sentiment trends, identify the main discrete emotions that affect customers’ ratings in a restaurant setting and identify constituents of influential emotions. Design/methodology/approach A total of 683,610 online restaurant reviews downloaded from Dianping.com were analyzed by a sentiment dictionary optimized by the authors; the main emotions (joy, love, trust, anger, sadness and surprise) that affect online ratings were explored by using multiple linear regression methods. After tracking these sentiment review texts, Latent Dirichlet Allocation (LDA) and LDA models with term frequency-inverse document frequency as weights were used to find the factors that constitute influential emotions. Findings The results show that it is viable to optimize or expand sentiment dictionary by word similarity. The findings highlight that love and anger have the highest effect on online ratings. The main factors that constitute consumers’ anger (local characteristics, incorrect food portions and unobtrusive location) and love (comfortable dining atmosphere, obvious local characteristics and complete supporting services) are identified. Different from previous studies, negativity bias is not observed, which poses a question of whether it has to do with Chinese culture. Practical implications These findings can help managers monitor the true quality of restaurant service in an area on time. Based on the results, restaurant operators can better decide which aspects they should pay more attention to; platforms can operate better and can have more manageable webpage settings; and consumers can easily capture the quality of restaurants to make better purchase decisions. Originality/value This study builds upon the existing general sentiment dictionary in Chinese and, to the best of the authors’ knowledge, is the first to provide a restaurant-domain-specific sentiment dictionary and use it for analysis. It also reveals the constituents of two prominent emotions (love and anger) in the case of restaurant reviews.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Through this model, they demonstrated that emotions mediate the impact of perceived quality on behavioral intention (Ribeiro and Prayag, 2019). Recently, Rocklage et al (2021) concluded that emotionality in text may be more indicative of the success of a product or service compared to average star rating.…”

Section: Introductionmentioning

confidence: 99%

What affects the online ratings of restaurant consumers: a research perspective on text-mining big data analysis

Mehraliyev

et al. 2022

IJCHM

View full text Add to dashboard Cite

show abstract

“…We can also consider the impact of time on building a reputation system because normal evaluators rarely generate a large number of ratings in a short time, whereas spammers may do so. Additionally, we should also pay attention to the emotional language in the text comments of the evaluation system, which can provide more meaningful information to individuals [46].…”

Section: Discussionmentioning

confidence: 99%

Improving the Performance of Reputation Evaluation by Combining a Network Structure With Nonlinear Recovery

Han

Jiang

et al. 2022

Front. Phys.

View full text Add to dashboard Cite

Characterizing the reputation of an evaluator is particularly significant for consumers to obtain useful information from online rating systems. Furthermore, overcoming the difficulties of spam attacks on a rating system and determining the reliability and reputation of evaluators are important topics in the research. We have noticed that most existing reputation evaluation methods rely only on using the evaluator’s rating information and abnormal behaviour to establish a reputation system, which disregards the systematic aspects of the rating systems, by including the structure of the evaluator-object bipartite network and nonlinear effects. In this study, we propose an improved reputation evaluation method by combining the structure of the evaluator-object bipartite network with rating information and introducing penalty and reward factors. The proposed method is empirically analyzed on a large-scale artificial data set and two real data sets. The results have shown that this method has better performance than the original correlation-based and IARR2 in the presence of spamming attacks. Our work contributes a new idea to build reputation evaluation models in sparse bipartite rating networks.

show abstract

“…Text boasts important advantages over other forms of data used in social science. First, language is the most effective tool humans have devised for expressing ourselves, so there is little doubt that an explanation of one's attitude is more representative of their thoughts and feelings than, say, a Likert scale response (see Rocklage, Rucker, and Nordgren 2021). Second, digitally stored text exchanges are available to researchers in perfect fidelity, at least in principle.…”

Section: Introductionmentioning

confidence: 99%

Three families of automated text analysis

Loon¹

2022

Social Science Research

View full text Add to dashboard Cite

Mass-scale emotionality reveals human behaviour and marketplace success

Cited by 35 publications

References 40 publications

What affects the online ratings of restaurant consumers: a research perspective on text-mining big data analysis

What affects the online ratings of restaurant consumers: a research perspective on text-mining big data analysis

Improving the Performance of Reputation Evaluation by Combining a Network Structure With Nonlinear Recovery

Three families of automated text analysis

Contact Info

Product

Resources

About