An Empirical Investigation of Personalization Factors on TikTok

• URL: http://arxiv.org/abs/2201.12271v1
• Date: Fri, 28 Jan 2022 17:40:00 GMT
• Title: An Empirical Investigation of Personalization Factors on TikTok
• Authors: Maximilian Boeker, Aleksandra Urman
• Abstract summary: Despite the importance of TikTok's algorithm to the platform's success and content distribution, little work has been done on the empirical analysis of the algorithm. Using a sock-puppet audit methodology with a custom algorithm developed by us, we tested and analysed the effect of the language and location used to access TikTok. We identify that the follow-feature has the strongest influence, followed by the like-feature and video view rate.
• Score: 77.34726150561087
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: TikTok currently is the fastest growing social media platform with over 1 billion active monthly users of which the majority is from generation Z. Arguably, its most important success driver is its recommendation system. Despite the importance of TikTok's algorithm to the platform's success and content distribution, little work has been done on the empirical analysis of the algorithm. Our work lays the foundation to fill this research gap. Using a sock-puppet audit methodology with a custom algorithm developed by us, we tested and analysed the effect of the language and location used to access TikTok, follow- and like-feature, as well as how the recommended content changes as a user watches certain posts longer than others. We provide evidence that all the tested factors influence the content recommended to TikTok users. Further, we identified that the follow-feature has the strongest influence, followed by the like-feature and video view rate. We also discuss the implications of our findings in the context of the formation of filter bubbles on TikTok and the proliferation of problematic content.

Related papers

• Contrastive Learning for Implicit Social Factors in Social Media Popularity Prediction [12.798988947331596]
  We study factors introduced by social platforms that impact post popularity. These factors include content relevance, user influence similarity, and user identity. We propose three implicit social factors related to popularity, including content relevance, user influence similarity, and user identity.
  arXiv  Detail & Related papers  (2024-10-12T03:25:11Z)
• Modeling offensive content detection for TikTok [0.0]
  This research undertakes the collection and analysis of TikTok data containing offensive content. It builds a series of machine learning and deep learning models for offensive content detection.
  arXiv  Detail & Related papers  (2024-08-29T18:47:41Z)
• Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content [66.71102704873185]
  We test for user strategization by conducting a lab experiment and survey. We find strong evidence of strategization across outcome metrics, including participants' dwell time and use of "likes" Our findings suggest that platforms cannot ignore the effect of their algorithms on user behavior.
  arXiv  Detail & Related papers  (2024-05-09T07:36:08Z)
• Can Probabilistic Feedback Drive User Impacts in Online Platforms? [26.052963782865294]
  A common explanation for negative user impacts of content recommender systems is misalignment between the platform's objective and user welfare. In this work, we show that misalignment in the platform's objective is not the only potential cause of unintended impacts on users. The source of these user impacts is that different pieces of content may generate observable user reactions (feedback information) at different rates.
  arXiv  Detail & Related papers  (2024-01-10T18:12:31Z)
• User Strategization and Trustworthy Algorithms [81.82279667028423]
  We show that user strategization can actually help platforms in the short term. We then show that it corrupts platforms' data and ultimately hurts their ability to make counterfactual decisions.
  arXiv  Detail & Related papers  (2023-12-29T16:09:42Z)
• Bag of Tricks for Training Data Extraction from Language Models [98.40637430115204]
  We investigate and benchmark tricks for improving training data extraction using a publicly available dataset. The experimental results show that several previously overlooked tricks can be crucial to the success of training data extraction.
  arXiv  Detail & Related papers  (2023-02-09T06:46:42Z)
• Modeling Content Creator Incentives on Algorithm-Curated Platforms [76.53541575455978]
  We study how algorithmic choices affect the existence and character of (Nash) equilibria in exposure games. We propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
  arXiv  Detail & Related papers  (2022-06-27T08:16:59Z)
• Fine-Grained Visual Entailment [51.66881737644983]
  We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
  arXiv  Detail & Related papers  (2022-03-29T16:09:38Z)
• Slapping Cats, Bopping Heads, and Oreo Shakes: Understanding Indicators of Virality in TikTok Short Videos [11.089339341624996]
  We study what elements of short videos posted on TikTok contribute to their virality. Our research highlights the characteristics that distinguish viral from non-viral TikTok videos.
  arXiv  Detail & Related papers  (2021-11-03T18:17:16Z)
• DFW-PP: Dynamic Feature Weighting based Popularity Prediction for Social Media Content [4.348651617004765]
  Over-saturation of content on social media platforms has persuaded us to identify the important factors that affect content popularity. We propose the DFW-PP framework, to learn the importance of different features that vary over time. The proposed method is experimented with a benchmark dataset, to show promising results.
  arXiv  Detail & Related papers  (2021-10-16T08:40:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.