Predicting the popularity of web 2.0 items based on user comments

In the current Web 2.0 era, the popularity of Web resources fluctuates ephemerally, based on trends and social interest. As a result, content-based relevance signals are insufficient to meet users' constantly evolving information needs in searching for Web 2.0 items. Incorporating future popularity into ranking is one way to counter this. However, predicting popularity as a third party (as in the case of general search engines) is difficult in practice, due to their limited access to item view histories. To enable popularity prediction externally without excessive crawling, we propose an alternative solution by leveraging user comments, which are more accessible than view counts. Due to the sparsity of comments, traditional solutions that are solely based on view histories do not perform well. To deal with this sparsity, we mine comments to recover additional signal, such as social influence. By modeling comments as a time-aware bipartite graph, we propose a regularization-based ranking algorithm that accounts for temporal, social influence and current popularity factors to predict the future popularity of items. Experimental results on three real-world datasets --- crawled from YouTube, Flickr and Last.fm --- show that our method consistently outperforms competitive baselines in several evaluation tasks.

• Publication year

  2014

• Venue

  Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

• Publication date

  2014-07-03

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/2600428.2609558
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Explicit factor models for explainable recommendation based on phrase-level sentiment analysis

  2014cited by this paper
• Comment-based multi-view clustering of web 2.0 items

  2014cited by this paper
• Incorporating popularity in topic models for social network analysis

  2013cited by this paper
• A peek into the future: predicting the evolution of popularity in user generated content

  2013cited by this paper
• Using early view patterns to predict the popularity of youtube videos

  2013influential reference
• Care to comment?: recommendations for commenting on news stories

  2012cited by this paper
• Modeling and predicting behavioral dynamics on the web

  2012influential reference
• Tweet Recommendation with Graph Co-Ranking

  2012cited by this paper
• A straw shows which way the wind blows: ranking potentially popular items from early votes

  2012cited by this paper
• Leveraging user comments for aesthetic aware image search reranking

  2012influential reference
• Can Social Features Help Learning to Rank YouTube Videos?

  2012cited by this paper
• Re-tweeting from a linguistic perspective

  2012cited by this paper
• Attention prediction on social media brand pages

  2011cited by this paper
• Everyone's an influencer: quantifying influence on twitter

  2011cited by this paper
• Recommender systems with social regularization

  2011cited by this paper
• Predicting the popularity of online articles based on user comments

  2011cited by this paper
• Improved video categorization from text metadata and user comments

  2011cited by this paper
• The tube over time: characterizing popularity growth of youtube videos

  2011cited by this paper
• Using a model of social dynamics to predict popularity of news

  2010cited by this paper
• On Popularity in the Blogosphere

  2010influential reference
• Digging Digg: Comment Mining, Popularity Prediction, and Social Network Analysis

  2009cited by this paper
• A generalized Co-HITS algorithm and its application to bipartite graphs

  2009cited by this paper
• A random walk on the red carpet: rating movies with user reviews and pagerank

  2008cited by this paper
• Predicting the popularity of online content

  2008cited by this paper
• Comments-oriented document summarization: understanding documents with readers' feedback

  2008cited by this paper
• Leave a Reply: An Analysis of Weblog Comments

  2006cited by this paper
• Time weight collaborative filtering

  2005cited by this paper
• Probability and Computing: Randomized Algorithms and Probabilistic Analysis

  2005cited by this paper
• A uniform approach to accelerated PageRank computation

  2005cited by this paper
• Regularization on Discrete Spaces

  2005cited by this paper
• Maintaining time-decaying stream aggregates

  2003cited by this paper
• The Analysis of Time Series : An Introduction, Sixth Edition

  2003cited by this paper
• Topic-sensitive PageRank

  2002cited by this paper
• IR evaluation methods for retrieving highly relevant documents

  2000cited by this paper
• The stochastic approach for link-structure analysis (SALSA) and the TKC effect

  2000cited by this paper
• The PageRank Citation Ranking : Bringing Order to the Web

  1999influential reference
• Authoritative sources in a hyperlinked environment

  1999influential reference
• Spectral Graph Theory

  1996cited by this paper
• The Analysis of Time Series: An Introduction

  1990cited by this paper

• SMPV: Social Media Prediction for Videos

  2025cites this paper
• Signals in the Noise: Decoding Unexpected Engagement Patterns on Twitter

  2025cites this paper
• Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction

  2025cites this paper
• Attention-inspired text-based recommender system with explanatory capabilities

  2025cites this paper
• Contrastive Learning for Implicit Social Factors in Social Media Popularity Prediction

  2024cites this paper
• A Survey of Deep Learning-Based Information Cascade Prediction

  2024cites this paper
• SMP Challenge Summary: Social Media Prediction Challenge

  2024cites this paper
• Improved negative sampling method in collaborative filtering recommendation based on Generative adversarial network

  2024cites this paper
• Predicting popularity trend in social media networks with multi-layer temporal graph neural networks

  2024cites this paper
• Improving Social Media Popularity Prediction with Multiple Post Dependencies

  2023cites this paper
• Predicting the Popularity of Information on Social Platforms without Underlying Network Structure

  2023cites this paper
• Contrastive sequential interaction network learning on co-evolving Riemannian spaces

  2023cites this paper
• SINCERE: Sequential Interaction Networks representation learning on Co-Evolving RiEmannian manifolds

  2023cites this paper
• An Interpretable Preference Learning Model Admitting Dynamic and Context-Dependent Preferences

  2023cites this paper
• Hashtag recommendation for enhancing the popularity of social media posts

  2023cites this paper
• Linear vs. Non-Linear Embedding Methods in Recommendation Systems

  2022cites this paper
• Affective Signals in a Social Media Recommender System

  2022cites this paper
• Academic social networks metrics: an effective indicator for university performance?

  2022cites this paper
• Social Media Popularity Prediction Based on Multi-Modal Self-Attention Mechanisms

  2022cites this paper
• Selection bias mitigation in recommender system using uninteresting items based on temporal visibility

  2022cites this paper
• Which social media posts generate the most buzz? Evidence from WeChat

  2021cites this paper
• DNCP: An attention-based deep learning approach enhanced with attractiveness and timeliness of News for online news click prediction

  2021cites this paper
• Optimizing Prediction of YouTube Video Popularity Using XGBoost

  2021cites this paper
• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances

  2021cites this paper
• Evolutionary Prediction of Nonstationary Event Popularity Dynamics of Weibo Social Network Using Time-Series Characteristics

  2021cites this paper
• Dual-Embedding based Deep Latent Factor Models for Recommendation

  2021cites this paper
• Latent factor recommendation models for integrating explicit and implicit preferences in a multi-step decision-making process

  2021cites this paper
• A Brief Survey of Graph Ranking Methods

  2021cites this paper
• GraphShop: Graph-based Approach for Shop-type Recommendation

  2021cites this paper
• Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes

  2021cites this paper
• FANG: Leveraging Social Context for Fake News Detection Using Graph Representation

  2020cites this paper
• Improving Implicit Recommender Systems with Auxiliary Data

  2020cites this paper
• A Bayesian learning model for design-phase service mashup popularity prediction

  2020cites this paper
• A Hybrid Recommender Method Based on Multiple Dimension Attention Analysis

  2020cites this paper
• Context-Aware Network Analysis of Music Streaming Services for Popularity Estimation of Artists

  2020cites this paper
• A Prediction Method of Peak Time Popularity Based on Twitter Hashtags

  2020cites this paper
• Minimize Social Network Rumors Based on Rumor Path Tree

  2020cites this paper
• A Feature Generalization Framework for Social Media Popularity Prediction

  2020cites this paper
• Efficient Synergetic Filtering in Big Dataset using Neural Network Technique

  2020cites this paper
• Muet Blogging: An Integral Platform for Students Projects

  2020cites this paper
• Predicting the active period of popularity evolution: A case study on Twitter hashtags

  2020cites this paper
• Nonlinear dynamics model for social popularity prediction based on multivariate chaotic time series

  2019cites this paper
• Diversifying personalized mobile multimedia application recommendations through the Latent Dirichlet Allocation and clustering optimization

  2019cites this paper
• Matrix Factorization for Personalized Recommendation With Implicit Feedback and Temporal Information in Social Ecommerce Networks

  2019cites this paper
• User-Aware Folk Popularity Rank: User-Popularity-Based Tag Recommendation That Can Enhance Social Popularity

  2019cites this paper
• Feature Construction for Posts and Users Combined with LightGBM for Social Media Popularity Prediction

  2019cites this paper
• Something’s Brewing! Early Prediction of Controversy-causing Posts from Discussion Features

  2019cites this paper
• Expert recommendation in community question answering: a review and future direction

  2019cites this paper
• Exploiting Social Data to Enhance Web Search

  2019cites this paper
• Product Aspect Ranking and Its Application

  2019cites this paper
• Fast Matrix Factorization With Nonuniform Weights on Missing Data

  2018cites this paper
• Learning on Partial-Order Hypergraphs

  2018cites this paper
• Missing Data Modeling with User Activity and Item Popularity in Recommendation

  2018cites this paper
• Product Adoption Rate Prediction in a Competitive Market

  2018cites this paper
• Entity Retrieval and Text Mining for Online Reputation Monitoring

  2018cites this paper
• CrowdPop

  2018cites this paper
• Scholars Archive

  2018influential citation
• Popularity Prediction for Single Tweet Based on Heterogeneous Bass Model

  2018cites this paper
• User-guided Hierarchical Attention Network for Multi-modal Social Image Popularity Prediction

  2018cites this paper
• Venue Prediction for Social Images by Exploiting Rich Temporal Patterns in LBSNs

  2018cites this paper
• A Graph-Theoretic Fusion Framework for Unsupervised Entity Resolution

  2018cites this paper
• Factorization Meets Memory Network: Learning to Predict Activity Popularity

  2018cites this paper
• DELF: A Dual-Embedding based Deep Latent Factor Model for Recommendation

  2018cites this paper
• Matrix factorization for recommendation with explicit and implicit feedback

  2018cites this paper
• LRMM: Learning to Recommend with Missing Modalities

  2018cites this paper
• A Vocabulary for Growth: Topic Modeling of Content Popularity Evolution

  2018cites this paper
• CrowdPop: Leveraging Multi-Source Crowd-Contributed Data for App Evolutionary Pattern Analysis and Popularity Prediction

  2018cites this paper
• SocialGQ: Towards Semantically Approximated and User-aware Querying of Social-Graph Data

  2018cites this paper
• Predicting Hashtag Popularity of Social Emergency by a Robust Feature Extraction Method

  2017cites this paper
• POI Popularity Prediction via Hierarchical Fusion of Multiple Social Clues

  2017cites this paper
• Neural Factorization Machines for Sparse Predictive Analytics

  2017cites this paper
• Predicting Key Events in the Popularity Evolution of Online Information

  2017cites this paper
• Version-sensitive mobile App recommendation

  2017cites this paper
• LARM: A Lifetime Aware Regression Model for Predicting YouTube Video Popularity

  2017cites this paper
• News censorship in online social networks: A study of circumvention in the commentsphere

  2017cites this paper
• Multimodal Context-Aware Recommender for Post Popularity Prediction in Social Media

  2017influential citation
• On the Measurement and Prediction of Web Content Utility: A Review

  2017cites this paper
• Event Early Embedding: Predicting Event Volume Dynamics at Early Stage

  2017cites this paper
• Modeling Data Correlations in Recommendation

  2017cites this paper
• Classification by Retrieval: Binarizing Data and Classifiers

  2017cites this paper
• Multi-dependent Latent Dirichlet Allocation

  2017cites this paper
• Neural Collaborative Filtering

  2017cites this paper
• Cross-Platform App Recommendation by Jointly Modeling Ratings and Texts

  2017cites this paper
• Predicting the Success of Online Petitions Leveraging Multidimensional Time-Series

  2017cites this paper
• Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks

  2017cites this paper
• Leveraging social information for personalized search

  2017cites this paper
• The success of hashing technique is indeed beyond fast image search

  2017cites this paper
• Temporal Influence Blocking: Minimizing the Effect of Misinformation in Social Networks

  2017cites this paper
• A Fine-Grained Latent Aspects Model for Recommendation: Combining Each Rating with Its Associated Review

  2017cites this paper
• Understanding and predicting the peak popularity of bursting hashtags

  2017cites this paper
• BiRank: Towards Ranking on Bipartite Graphs

  2017cites this paper
• Profiling, Modelling and Facilitating Online Activism

  2017influential citation
• Prediction of Video Popularity in the Absence of Reliable Data from Video Hosting Services: Utility of Traces Left by Users on the Web

  2016influential citation
• Social networks and information retrieval, how are they converging? A survey, a taxonomy and an analysis of social information retrieval approaches and platforms

  2016cites this paper
• A Novel Time Series Approach for Predicting the Long-Term Popularity of Online Videos

  2016cites this paper
• Time Matters: Multi-scale Temporalization of Social Media Popularity

  2016influential citation
• Learning from the News: Predicting Entity Popularity on Twitter

  2016cites this paper
• PerSaDoR: Personalized social document representation for improving web search

  2016cites this paper
• Micro Tells Macro: Predicting the Popularity of Micro-Videos via a Transductive Model

  2016cites this paper
• Fast Matrix Factorization for Online Recommendation with Implicit Feedback

  2016cites this paper