Social Indexing of TV Programs: Detection and Labeling of Significant TV Scenes by Twitter Analysis

Nakazawa, Masami; Erdmann, Maike; Hoashi, Keiichiro; Ono, Chihiro

doi:10.1109/waina.2012.188

Cited by 15 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms for peak detection applied to streams of tweets already proved their usefulness in effectively segmenting a TV program (Nakazawa, Erdmann, Hoashi, & Ono, ; Shamma, Kennedy, & Churchill, , ; Shamma et al, ). On this basis, we applied the peak detection algorithm described by Marcus and colleagues () to the stream of original tweets in our dataset, ending up with 286 detected peaks with their respective windows (span of n minutes around the peak).…”

Section: Methodsmentioning

confidence: 99%

Second Screen and Participation: A Content Analysis on a Full Season Dataset of Tweets

2014

View full text Add to dashboard Cite

The practice of using a “second screen” while following a television program is quickly becoming a widespread phenomenon. When the secondary device is used for comments about programs, most discussions take place on popular social media such as Facebook and Twitter. Previous research pointed out the value of these conversations in understanding the behavior of “networked publics.” Building upon this background, this article presents the first study on a complete dataset of tweets (2,489,669) that span an entire season of a TV genre (1,076 episodes of talk shows). A content analysis of the tweets created during the season's most engaging moments indicates a relationship between typology of broadcasted scenes, style of comments, and the way participation (audience and political) is played

show abstract

Section: Methodsmentioning

confidence: 99%

Second Screen and Participation: A Content Analysis on a Full Season Dataset of Tweets

2014

View full text Add to dashboard Cite

show abstract

“…Algorithms for peak detection applied to streams of tweets have already proven to be useful in effectively segmenting a TV program (Nakazawa, Erdmann, Hoashi, & Ono, 2012;Shamma, Kennedy, & Churchill, 2009Shamma, Yew, Kennedy, & Churchill, 2011). On this basis, we applied the peak detection algorithm described by Adam Marcus and colleagues (2011) to the stream of original tweets created during the on-air time of the 9 episodes of The X Factor and 28 episodes of Servizio Pubblico.…”

Section: Peak Detectionmentioning

confidence: 99%

Understanding Engagement and Willingness to Speak Up in Social-Television: A Full-Season, Cross-Genre Analysis of TV Audience Participation on Twitter

et al. 2015

View full text Add to dashboard Cite

The widespread use of digital platforms has changed the way people watch television. Despite an abundance of empirical studies, full-season, cross-genre analyses of different TV formats are rare. Based on a data set of 1,383,414 tweets, this study aims to close this gap by comparing Twitter commentaries around the 2012-2013 seasons of the Italian edition of The X Factor and the political talk show Servizio Pubblico. For each episode, we identify peaks of Twitter engagement and analyze the corresponding TV scene, revealing the role played by suspense and surprise in catalyzing the engagement of online audiences. A content analysis of 12,640 tweets created during peaks of engagement reveals how willingness to speak up varies when the topic is politics rather than entertainment.

show abstract

“…Highlights consist of important scenes such as scoring and home runs. Therefore, since important scene detection methods are necessary for the generation of highlights, various detection methods have been proposed [2][3][4][5][6][7][8]. The methods in [2][3][4] using videos detect important scenes by applying a hidden Markov model and a maximum entropy model to player movements and cheers from the audiences obtained from the target videos.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, conventional video-based methods are effective for the representation of visual information of players and audiences. On the other hand, along with the development of microblogging services, methods using Twitter (https: //twitter.com/ (accessed on 12 March 2021) for the detection of important scenes have been proposed [5][6][7]. By using Twitter, which is one of the microblogging services, the reactions of viewers during games can be obtained.…”

Section: Introductionmentioning

confidence: 99%

Detection of Important Scenes in Baseball Videos via a Time-Lag-Aware Multimodal Variational Autoencoder

Hirasawa

Maeda

Ogawa

et al. 2021

Sensors

View full text Add to dashboard Cite

A new method for the detection of important scenes in baseball videos via a time-lag-aware multimodal variational autoencoder (Tl-MVAE) is presented in this paper. Tl-MVAE estimates latent features calculated from tweet, video, and audio features extracted from tweets and videos. Then, important scenes are detected by estimating the probability of the scene being important from estimated latent features. It should be noted that there exist time-lags between tweets posted by users and videos. To consider the time-lags between tweet features and other features calculated from corresponding multiple previous events, the feature transformation based on feature correlation considering such time-lags is newly introduced to the encoder in MVAE in the proposed method. This is the biggest contribution of the Tl-MVAE. Experimental results obtained from actual baseball videos and their corresponding tweets show the effectiveness of the proposed method.

show abstract

Social Indexing of TV Programs: Detection and Labeling of Significant TV Scenes by Twitter Analysis

Cited by 15 publications

References 7 publications

Second Screen and Participation: A Content Analysis on a Full Season Dataset of Tweets

Second Screen and Participation: A Content Analysis on a Full Season Dataset of Tweets

Understanding Engagement and Willingness to Speak Up in Social-Television: A Full-Season, Cross-Genre Analysis of TV Audience Participation on Twitter

Detection of Important Scenes in Baseball Videos via a Time-Lag-Aware Multimodal Variational Autoencoder

Contact Info

Product

Resources

About