Exploiting Surface Features for the Prediction of Podcast Preference

Tsagkias, Manos; Larson, Martha; Rijke, Maarten de

doi:10.1007/978-3-642-00958-7_42

Cited by 6 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lerman et al [7] forecast the public opinion of political candidates from objective news articles. Finally, Tsagkias et al [13] predict podcast preference using surface features extracted from podcast RSS feeds.…”

Section: Related Workmentioning

confidence: 99%

Predicting the volume of comments on online news stories

Tsagkias

Weerkamp

Rijke

2009

Proceedings of the 18th ACM Conference on Information and Knowledge Management

Self Cite

129

108

View full text Add to dashboard Cite

On-line news agents provide commenting facilities for readers to express their views with regard to news stories. The number of user supplied comments on a news article may be indicative of its importance or impact. We report on exploratory work that predicts the comment volume of news articles prior to publication using five feature sets. We address the prediction task as a two stage classification task: a binary classification identifies articles with the potential to receive comments, and a second binary classification receives the output from the first step to label articles "low" or "high" comment volume. The results show solid performance for the former task, while performance degrades for the latter.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting the volume of comments on online news stories

Tsagkias

Weerkamp

Rijke

2009

Proceedings of the 18th ACM Conference on Information and Knowledge Management

Self Cite

129

108

View full text Add to dashboard Cite

show abstract

“…By using the metadata we are able to ensure that this feature remains extractable with only a surface observation of the podcast, i.e., there is no need for processing or analysis of the audio file. We encode the regularity with which a podcast is published with a Fast Fourier Transform‐based measure, which is described in further detail in Tsagkias, Larson, and de Rijke (2009). We also include features that are less precise in their ability to reflect regularity, but are simpler to compute.…”

Section: Validating the Podcred Frameworkmentioning

confidence: 99%

Predicting podcast preference: An analysis framework and its application

Tsagkias

Larson

Rijke

2009

J. Am. Soc. Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Finding worthwhile podcasts can be difficult for listeners since podcasts are published in large numbers and vary widely with respect to quality and repute. Independently of their informational content, certain podcasts provide satisfying listening material while other podcasts have little or no appeal. In this paper we present PodCred, a framework for analyzing listener appeal, and we demonstrate its application to the task of automatically predicting the listening preferences of users. First, we describe the PodCred framework, which consists of an inventory of factors contributing to user perceptions of the credibility and quality of podcasts. The framework is designed to support automatic prediction of whether or not a particular podcast will enjoy listener preference. It consists of four categories of indicators related to the Podcast Content, the Podcaster, the Podcast Context, and the Technical Execution of the podcast. Three studies contributed to the development of the PodCred framework: a review of the literature on credibility for other media, a survey of prescriptive guidelines for podcasting, and a detailed data analysis. Next, we report on a validation exercise in which the PodCred framework is applied to a real-world podcast preference prediction task. Our validation focuses on select framework indicators that show promise of being both discriminative and readily accessible. We translate these indicators into a set of easily extractable "surface" features and use them to implement a basic classification system. The experiments carried out to evaluate system use popularity levels in iTunes as ground truth and demonstrate that simple surface features derived from the PodCred framework are indeed useful for classifying podcasts. IntroductionPodcasts are audio series published online. As new episodes of a podcast are created, they are added to the podcast feed and are distributed over the Internet (Patterson, 2006;van Gils, 2008). Users either download episodes individually for listening or subscribe to the feed of a podcast, so that new episodes are automatically downloaded as they are published. Not every podcast is an equally valuable source of information and entertainment. Finding worthwhile podcasts among the large volumes of podcasts available online, which vary widely in quality and repute, can be a daunting task for podcast listeners and subscribers. We present an analysis framework, called PodCred, for assessing the credibility and quality on podcasts on the Internet. The framework is designed to support prediction of whether a listener will select one podcast over another, given that both podcasts contain comparable informational content. We demonstrate the utility of the framework with a validation exercise that demonstrates its ability to support prediction of listener appeal, i.e., the potential of a podcast to enjoy favor and preference among users. 1 Podcasts are compared to radio programs by some definitions (Heffernan, 2005;Matthews, 2006). However, podcasting on the Internet and ra...

show abstract

“…It is a coarse assignment method of weights. Compared to this "radical attitude" behind NCM, in CM each observed vote contributes probabilistically to both π c and πm as shown in Equations (15) and (16). Specifically, for a vote x i on an item with the popularity q i, the value of P r(zc|xi, qi) contributes its conformer personality while that of P r(z m|xi, qi) contributes its maverick personality.…”

Section: E-stepmentioning

confidence: 99%

“…Other existing works integrate user comments [12,15,16,14]. This information, however, is not always available compared with votes.…”

Section: Related Workmentioning

confidence: 99%

A straw shows which way the wind blows

Yin

Luo²,

Wang³

et al. 2012

Proceedings of the Fifth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Prediction of popular items in online content sharing systems has recently attracted a lot of attention due to the tremendous need of users and its commercial values. Different from previous works that make prediction by fitting a popularity growth model, we tackle this problem by exploiting the latent conforming and maverick personalities of those who vote to assess the quality of on-line items. We argue that the former personality prompts a user to cast her vote conforming to the majority of the service community while on the contrary the later personality makes her vote different from the community. We thus propose a Conformer-Maverick (CM) model to simulate the voting process and use it to rank top-k potentially popular items based on the early votes they received. Through an extensive experimental evaluation, we validate our ideas and find that our proposed CM model achieves better performance than baseline solutions, especially for smaller k.

show abstract

Exploiting Surface Features for the Prediction of Podcast Preference

Cited by 6 publications

References 7 publications

Predicting the volume of comments on online news stories

Predicting the volume of comments on online news stories

Predicting podcast preference: An analysis framework and its application

A straw shows which way the wind blows

Contact Info

Product

Resources

About