Electronic word-of-mouth, box office revenue and social media

Baek, Hyunmi; Oh, Sehwan; Yang, Hee-dong; Ahn, JoongHo

doi:10.1016/j.elerap.2017.02.001

Cited by 54 publications

(35 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first set of features capture information about movies that is commonly considered in academic studies on movies (Baek et al 2017; Eliashberg, Anita, and Leenders 2006; Ghiassi, Lio, and Moon 2015; Litman and Ahn 1998; Narayan and Kadiyali 2015; Ravid 1999; Sharda and Delen 2006; Zufryden 1996). For each movie in each study, we collect the average critic rating (from Metacritic); the average user score (from Metacritic); the production budget (from IMDb, adjusted for inflation using the tool available at http://data.bls.gov/cgi-bin/cpicalc.pl); the maximum number of screens on which the movie was shown in the United States throughout the course of its run in theaters, known as “widest release” (available from Box Office Mojo; boxofficemojo.com), for which we also include a square term; the domestic box office performance (from IMDb, adjusted for inflation using the tool available at http://data.bls.gov/cgi-bin/cpicalc.pl); the Motion Picture Association of America (MPAA) rating (from IMDb) 10 ; the movie’s run time in minutes (from Box Office Mojo); a dummy variable equal to 1 if the movie was a sequel; the degree of competition faced by the movie at the time of its release, captured by two dummy variables (following Sharda and Delen [2006]): a “high competition” variable is equal to 1 for movies released in the months of June and November, and a “medium competition” is equal to 1 for movies released in the months of May, July, and December (release month was obtained from IMDb); “star power,” measured as the power of the highest rated star in the movie at the time of its release (following Elberse and Eliashberg 2003), where power is measured using the STARmeter rating provided by IMDb; a measure of activity on Twitter, based on the publicly available MovieTweetings database of Dooms, De Pessemier, and Martens (2013) (we use the total number of tweets about each movie in the database as a cumulative measure of activity); the time elapsed between the release of the movie in theatres (obtained from IMDb) and the release of the DVD (obtained from Amazon); and the sales rank of the movie’s DVD as of December 2017 (obtained from Amazon).…”

Section: Using Guided Lda Features As Input Into Predictive Consumer mentioning

confidence: 99%

Extracting Features of Entertainment Products: A Guided Latent Dirichlet Allocation Approach Informed by the Psychology of Media Consumption

Toubia¹,

Iyengar²,

Bunnell³

et al. 2018

Journal of Marketing Research

View full text Add to dashboard Cite

The authors propose a quantitative approach for describing entertainment products, in a way that allows for improving the predictive performance of consumer choice models for these products. Their approach is based on the media psychology literature, which suggests that people’s consumption of entertainment products is influenced by the psychological themes featured in these products. They classify psychological themes on the basis of the “character strengths” taxonomy from the positive psychology literature (Peterson and Seligman 2004). They develop a natural language processing tool, guided latent Dirichlet allocation (LDA), that automatically extracts a set of features of entertainment products from their descriptions. Guided LDA is flexible enough to allow features to be informed by psychological themes while allowing other relevant dimensions to emerge. The authors apply this tool to movies and show that guided LDA features help better predict movie-watching behavior at the individual level. They find this result with both award-winning movies and blockbuster movies. They illustrate the potential of the proposed approach in pure content-based predictive models of consumer behavior, as well as in hybrid predictive models that combine content-based models with collaborative filtering. They also show that guided LDA can improve the performance of models that predict aggregate outcomes.

show abstract

Section: Using Guided Lda Features As Input Into Predictive Consumer mentioning

confidence: 99%

Extracting Features of Entertainment Products: A Guided Latent Dirichlet Allocation Approach Informed by the Psychology of Media Consumption

Toubia¹,

Iyengar²,

Bunnell³

et al. 2018

Journal of Marketing Research

View full text Add to dashboard Cite

show abstract

“…Online feedback is regarded as an important information tool to help consumers understand the quality of services and products and interact with sellers, service providers, and other consumers [14-17]. With the development of telemedicine and telemedicine services, online feedback has been widely applied in the telemedicine markets [18].…”

Section: Introductionmentioning

confidence: 99%

Investigating the Effect of Paid and Free Feedback About Physicians' Telemedicine Services on Patients’ and Physicians’ Behaviors: Panel Data Analysis

Yang¹,

Zhang²

2019

J Med Internet Res

View full text Add to dashboard Cite

Background In recent years, paid online patient-physician interaction has been incorporated into the telemedicine markets. With the development of telemedicine and telemedicine services, online feedback has been widely applied, helping other patients to identify quality services. Recently, in China, a new type of service feedback has been applied to the telemedicine markets, namely, paid feedback. Patients who are satisfied with a physician’s online service can buy a virtual gift or give a tip to the physicians. This paid feedback can improve the reliability of service feedback and reduce the proportion of false information because it increases the cost for feedback providers. Paid online feedback can benefit the physicians, such as by providing them with monetary incentives; however, research on the impacts and value of such paid feedback from the physician perspective in the telemedicine markets is scant. To fill this research gap, this study was designed to understand the role of paid feedback by developing a research model based on the theories of signaling and self-determination. Objective This study aimed to explore the effects of free and paid feedback on patients’ choice and physicians’ behaviors as well as to investigate the substitute relationship between these 2 types of feedback in the telemedicine markets. Methods A JAVA software program was used to collect online patient-doctor interaction data over a 6-month period from a popular telemedicine market in China (Good Physician Online). This study drew on a 2-equation panel model to test the hypotheses. Both fixed and random effect models were used to estimate the combined effects of paid feedback and free feedback on patients’ choice and physicians’ contribution. Finally, the Hausman test was adopted to investigate which model is better to explain our empirical results. Results The results of this study show that paid feedback has a stronger effect on patients’ choice (a 5 =0.566; t 2192 =9.160; P <.001) and physicians’ contribution (β 4 =1.332; t 2193 =11.067; P <.001) in telemedicine markets than free feedback. Moreover, our research also proves that paid feedback and free feedback have a substitute relationship in determining patients’ and physicians’ behaviors (a 6 =−0.304; t 2191 =−5.805; P <.001 and β 5 =−0.823; t 2192 =−8.136; P <.001). Conclusions Our findings contribute to the extant literature on service feedback in the telemedicine markets and provide insight for relevant stakeholders into how to design an effective f...

show abstract

“…We designed a web crawler by Python with Scrapy, which captures these reviews, a total 60,012 reviews from 95 movies between 4 November 2013 and 26 July 2018. Our movie volume was commonly used in previous works [30,57]. Figure 1 shows an example of an audience member's review on IMDb.…”

Section: Audience Reviewmentioning

confidence: 99%

Electronic word-of-mouth effects on studio performance leveraging attention-based model

Yang

Hao

Qing

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Electronic word-of-mouth, box office revenue and social media

Cited by 54 publications

References 27 publications

Extracting Features of Entertainment Products: A Guided Latent Dirichlet Allocation Approach Informed by the Psychology of Media Consumption

Extracting Features of Entertainment Products: A Guided Latent Dirichlet Allocation Approach Informed by the Psychology of Media Consumption

Investigating the Effect of Paid and Free Feedback About Physicians' Telemedicine Services on Patients’ and Physicians’ Behaviors: Panel Data Analysis

Electronic word-of-mouth effects on studio performance leveraging attention-based model

Contact Info

Product

Resources

About