How useful are your comments?: analyzing and predicting youtube comments and comment ratings

By Stefan Siersdorfer, Sergiu Chelaru, Wolfgang Nejdl, José San Pedro. The Web Conference, 2010

362 citations recorded by the source corpus.

An analysis of the social video sharing platform YouTube reveals a high amount of community feedback through comments for published videos as well as through meta ratings for these comments. In this paper, we present an in-depth study of commenting and comment rating behavior on a sample of more than 6 million comments on 67,000 YouTube videos for which we analyzed dependencies between comments, views, comment ratings and topic categories. In addition, we studied the influence of sentiment expressed in comments on the ratings for these comments using the SentiWordNet thesaurus, a lexical WordNet-based resource containing sentiment annotations. Finally, to predict community acceptance for comments not yet rated, we built different classifiers for the estimation of ratings for these comments. The results of our large-scale evaluations are promising and indicate that community feedback on already rated comments can help to filter new unrated comments or suggest particularly useful but still unrated comments.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/3fc109c976bf1c3f06aba9310f86dcd0c124ab41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

You Watch, You Give, and You Engage: A Study of Live Streaming Practices in China (2018, methodology): “The commenting system on YouTube was analyzed by Siersdorfer [30] and it was found that most comments were concentrated on a small portion of the most popular videos.”
Characterizing and curating conversation threads: expansion, focus, volume, re-entry (2013, background): “Quality of posts or comments, as determined by ratings, is potentially also relevant; see for example Siersdorfer et al. [22].”
Analysis of user comments: An approach for software requirements evolution (2013, methodology): “Topic modeling, including unsupervised analysis and automatic inference of semantic topics, has previously been used to extract opinions from text corpora such as Twitter, YouTube, and blogs and the results have been used to suggest other relevant items (movies/videos, people, events, and groups) to”
Modelling input texts: from Tree Kernels to Deep Learning (2015, background): “[147] focus on exploiting user ratings (the counts of ‘thumbs up/down’ as flagged by other users) of YouTube video comments to train classifiers to predict the community acceptance of new comments.”
How Community Feedback Shapes User Behavior (2014, methodology): “While other more complex measures could result in slightly higher R2, we subsequently use p = P/(P +N) because it is both intuitive and fairly robust.”