Search results

Despite the growing importance of online word-of-mouth (WOM) with regard to television (TV) ratings, it is usually excluded from early prediction models. The purpose of this paper is to investigate the role of online WOM in TV ratings predictions, focussing on whether the incorporation of online WOM could improve predictions of TV ratings, and extracts meaningful rules for decision-making.

The author uses online WOM as a potential predictive variable in the TV ratings prediction model. The author matches a list of programs based on TV ratings for the movie channel with internet user reviews and TV ratings information from Yahoo! Movies (YM) and XYZ Company. The data set includes 71 movies, for which the data were analyzed with a hybrid model.

Grey relational analysis shows that online WOM is a useful ex ante determinant of TV ratings. As a predictive variable, it plays an essential role in enhancing TV ratings predictions. The experimental results also indicate that the proposed model surpasses other listed methods in terms of both accuracy and reduction of variables, while the proposed procedure yields a set of easily understandable decision rules that facilitate the interpretation of TV ratings information.

This paper identifies critical predictors of TV ratings and suggests that online WOM messages are a credible source. A hybrid model is developed to illustrate an intelligent prediction system for TV ratings.

The study demonstrates the effectiveness of online WOM and its impact on TV ratings. It offers an intelligent prediction system for TV ratings with practical implications for managers within the TV industry.

This study aims to examine entertainment TV shows' social media accounts to theoretically and practically explore the relationship between social media engagement and the performance (represented by ratings) of such shows.

By using the data of a popular TV show in the USA, The Voice, the present study examined the messages on the Facebook fan page of the show and how these messages correlated with the ratings of the show. Social media usage data in the course of three seasons (Seasons 10–12, 82 episodes in total) were collected from Facebook (N = 1,192,722 messages). Both regression and sentiment analysis were performed.

Overall, the findings revealed positive relationships of TV show ratings with both passive social media engagement (Facebook likes) and the number of official posts. However, active social media engagement was not positively related to show ratings.

By enhancing understanding of audience engagement with social media, our research extends knowledge related to the nature and development of viewer involvement with entertainment across different media platforms. Our results also help clarify how interpersonal communication (social media comments) and mass communication (TV programs) intersect. Practically, the findings could be applied to improve the interaction of TV audiences with show content, provide insights into the future of social TV development and inform decision-making amongst TV industry professionals.

Social media (e.g., e-WOM) and traditional media (e.g., media coverage) serve different roles in a firm's marketing activities and also interact with each other, which in turn affect the market outcome. In addition, how market outcome affects the two types of media in turn has not been examined, which brings the need for a holistic framework. The rare study that examines this relation mostly relies on the volume of media rather than the valence. This study examines the interdependent relation between the volume and valence of social media, the volume of traditional media and TV ratings.

Forty-one South Korean TV drama shows from October 2014 to March 2016 were analyzed using the 3SLS estimation to examine the interdependent relation between the variables.

First, the volume of traditional media has a negative effect on the volume of social media. Second, ratings negatively affect the valence of social media. Third, the volume of traditional media is found to have a negative effect on ratings. This is explained by the displacement effect.

This study is one of the very few studies that examine the interdependent relation between various earned media and market outcomes in one framework. In addition, it has originality in that it considers the valence of social media, which is an important dimension in analyzing earned media. Our results show negative effects of news media on TV ratings and e-WOM, which diverge from common intuition.

The purpose of this paper is to investigate the relation between average ratings (viewership) and the volume and valence of electronic word of mouth (e-WOM) for early episodes of TV shows.

Linear regression was performed in which the dependent variable is average TV ratings and main independent variables are volume and valence of e-WOM. The study used a Breusch–Pagan test to detect heteroscedasticity. Accordingly, the model is analyzed using heteroscedasticity-consistent standard error estimators.

The results show that the volume of the early e-WOM does not significantly contribute to explaining average ratings, but the valence does.

Because the advertising revenue of television broadcasters is determined according to expected TV ratings, the average ratings should be predicted as early as possible. This study shows that analyzing early e-WOM helps predict average ratings.

The purpose of this paper is to explore the interrelationship between television (TV) consumption (viewing ratings), engagement behaviors of different actors on Twitter (TV programs, media, celebrities and viewers) and the content of engagement behaviors (affective, program-related and social content).

TV ratings and Twitter data were obtained. The content of tweets was analyzed by means of a sentiment analysis. A vector auto regression model was used to understand the interrelationship between tweets of different actors and TV consumption.

First, the results showed a negative interrelationship between TV viewing and viewers’ tweeting behavior. Second, tweets by celebrities and media exhibited similar patterns and were both affected mostly by the number of tweets by viewers. Finally, the content of tweets matters. Affective tweets positively relate to TV viewing, and program-related and social content positively relates to the number of tweets by viewers.

The findings help us understand the online engagement ecosystem and provide insights into drivers of TV consumption and online engagement of different actors.

The results indicate that content producers may want to focus on stimulating affective conversations on Twitter to trigger more online and offline engagement. The results also call for rethinking the meaning of TV metrics.

While some studies have explored viewer interactions on Twitter, only a few studies have looked at the effects of such interactions on variables outside of social media, such as TV consumption. Moreover, the authors study the interrelations between Twitter interactions with TV consumption, which allows us to examine the effect of online engagement on offline behaviors and vice versa. Finally, the authors take different actors into account when studying real-life online engagement.

Both television and movie rating systems are used to inform parents, caregivers and prospective viewers about the content which will appear in a program. While rating systems are fallible, they do provide information prior to viewing. Unfortunately, television advertisements are not rated. Can a parent or caregiver feel confident that a child restricted to a particular level of viewing content will avoid being exposed to advertising content which exceeds the program rating? The purpose of this paper is to explore the content of advertisements relative to an established rating system.

Advertisements were assigned ratings based on the TV rating criteria. Comparisons between advertisement ratings and program ratings are provided. Additionally, advertisements are examined for unrated mature themes.

More than half of the advertisements analyzed across all program ratings were deemed appropriate for all audiences. However, it was discovered that advertisement content exceeded the content rating of the program during which it aired over 20 per cent of the time.

The findings show that the content of about one in every five television advertisements will have content that exceeds the content rating of the program in which the advertisement appears. This has the potential to undermine parental or caregiver restrictions on a child’s viewing content.

This article analyses how different configurations of stakeholders create opportunities for the production of popular TV sports contests. Based on qualitative methodologies, biathlon and cross-country skiing are used as contrasting cases. The paper concludes that the relative success of the International Biathlon Union is due to a favourable network position in relation to stakeholders. By comparison, the International Ski Federation suffers from a weak position within a dense stakeholder network.

One crucial but sometimes overlooked fact regarding the difference between observation in the cross-section and observation over time must be stated before proceeding further. Tempting though it is to draw conclusions about the dynamics of a process from cross-sectional observations taken as a snapshot of that process, it is a fallacious practice except under a very precise condition that is highly unlikely to obtain in processes of interest to the social scientist. That condition is known as ergodicity.

It is generally recognised that companies spend approximately 50% of their marketing budget on promotional activities. Advertising belongs to the most visible areas of a company’s activity. Therefore, it should not be surprising that the average recipient associates marketing with advertising, competitions and leaflets about new promotions delivered to houses or offices. Advertising, especially Internet advertising, is one of the most effective forms of marketing and one of the fastest developing areas of business. New channels of communication are emerging all the time – the Internet, digital television, mobile telephony; accompanied by new forms, such as the so-called ambient media. Advertising benefits from the achievements of many fields of science, that is, psychology, sociology, statistics, medicine and economics. At the same time, it combines science and the arts – it requires both knowledge and intuition. Contemporary advertising has different forms and areas of activity; yet it is always closely linked with the operations of a company – it is a form of marketing communication.

The indices of marketing communication presented in this chapter are generally known and used not only by advertising agencies but also by the marketing departments of many organisations. Brand awareness, advertising scope and frequency, the penetration index or the response rate belong to the most widely used indices; others, like the conversion rate or the affinity index, will get increasingly more significant along with the process of professionalisation of the environment of marketing specialists in Poland and with increased pressure on measuring marketing activities. Marketing indices are used for not only planning activities, but also their evaluation; some of them, such as telemarketing, mailing and coupons, provide an extensive array of possibilities of performance evaluation.

The widespread acceptance of various social platforms has increased the number of users posting about various services based on their experiences about the services. Finding out the intended ratings of social media (SM) posts is important for both organizations and prospective users since these posts can help in capturing the user’s perspectives. However, unlike merchant websites, the SM posts related to the service-experience cannot be rated unless explicitly mentioned in the comments. Additionally, predicting ratings can also help to build a database using recent comments for testing recommender algorithms in various scenarios.

In this study, the authors have predicted the ratings of SM posts using linear (Naïve Bayes, max-entropy) and non-linear (k-nearest neighbor, k-NN) classifiers utilizing combinations of different features, sentiment scores and emotion scores.

Overall, the results of this study reveal that the non-linear classifier (k-NN classifier) performed better than the linear classifiers (Naïve Bayes, Max-entropy classifier). Results also show an improvement of performance where the classifier was combined with sentiment and emotion scores. Introduction of the feature “factors of importance” or “the latent factors” also show an improvement of the classifier performance.

This study provides a new avenue of predicting ratings of SM feeds by the use of machine learning algorithms along with a combination of different features like emotional aspects and latent factors.