GhostLink: Latent Network Inference for Influence-aware Recommendation

  title={GhostLink: Latent Network Inference for Influence-aware Recommendation},
  author={Subhabrata Mukherjee and Stephan G{\"u}nnemann},
  journal={The World Wide Web Conference},
Social influence plays a vital role in shaping a user's behavior in online communities dealing with items of fine taste like movies, food, and beer. For online recommendation, this implies that users' preferences and ratings are influenced due to other individuals. Given only time-stamped reviews of users, can we find out who-influences-whom, and characteristics of the underlying influence network? Can we use this network to improve recommendation? While prior works in social-aware… 

Vibe check: social resonance learning for enhanced recommendation

This paper first formulate an item-aware user influence network that connects users who rate the same item and proposes a novel graph-based mutual learning framework, which captures the resonance influence from both user local correlations and global connections.

Instagrammers, Fashionistas, and Me: Recurrent Fashion Recommendation with Implicit Visual Influence

Experiments show that FIRN outperforms state-of-the-art fashion recommenders, especially for users who are most impacted by fashion influencers, and utilizing fashion bloggers can bring greater improvements in recommendation compared with using other potential sources of visual information.

Aspect-Similarity-Aware Historical Influence Modeling for Rating Prediction

An aspect-similarity-aware historical influence model for rating prediction using natural language processing techniques, focusing on the review-topic similarities, is proposed and it is shown that the method predicts ratings more accurately than the previous historical-inference-aware model.

Conductance and Social Capital: Modeling and Empirically Measuring Online Social Influence

The executives, media, and military are more influential than pandemic-related experts such as life scientists and healthcare professionals, and the generalized model outperforms the current state of the art approaches and corrects the inherent biases introduced by the widely used follower count.

Latent Network Embedding via Adversarial Auto-encoders

A latent network embedding model based on adversarial graph auto-encoders that achieves superior results compared with baseline models is proposed and an adversarial training that works as regularization to dislodge noises and improve the model robustness is introduced.

Future-Aware Diverse Trends Framework for Recommendation

This paper bridges the gap between the past preference and potential future preference by proposing the future-aware diverse trends (FAT) framework and demonstrates the proposed framework not only outperforms the state-of-the-art sequential recommendation methods across various metrics, but also makes complementary and fresh recommendations.



Inferring Latent Network from Cascade Data for Dynamic Social Recommendation

A new Implicit Dynamic Social Recommendation model is proposed, which infers latent social network from cascade data and can identify the dynamic changes in the users in time by using the latest updated social network to make recommendations.

Learning influence from heterogeneous social networks

A generative graphical model is proposed which leverages both heterogeneous link information and textual content associated with each user in the network to mine topic-level influence strength and greatly improves the accuracy of user behavior prediction.

Exploring social influence for recommendation: a generative model approach

Experimental results show that social influence captured based on the proposed probabilistic generative model, called social influenced selection (SIS), is effective for enhancing both item recommendation and group recommendation, essential for viral marketing, and useful for various user analysis.

Learning influence probabilities in social networks

This paper proposes models and algorithms for learning the model parameters and for testing the learned models to make predictions, and develops techniques for predicting the time by which a user may be expected to perform an action.

Personalized news recommendation via implicit social experts

An experimental study on implicit social recommendation

  • Hao Ma
  • Computer Science
  • 2013
This study conducts comprehensive experimental analysis on three recommendation datasets and indicates that implicit user and item social information, including similar and dissimilar relationships, can be employed to improve traditional recommendation methods.

Exploiting Social Information in Pairwise Preference Recommender System

Social PrefRec is envisioned, a social recommender that applies user preference mining and clustering techniques to incorporate social information on the pairwise preference recommenders, based on the hypothesis that user's preference is similar to or influenced by their connected friends.

Temporal recommendation on graphs via long- and short-term preference fusion

This work proposes Session-based Temporal Graph (STG) which simultaneously models users' long-term and short-term preferences over time and proposes a novel recommendation algorithm Injected Preference Fusion (IPF) and extends the personalized Random Walk for temporal recommendation.

Hidden factors and hidden topics: understanding rating dimensions with review text

This paper aims to combine latent rating dimensions (such as those of latent-factor recommender systems) with latent review topics ( such as those learned by topic models like LDA), which more accurately predicts product ratings by harnessing the information present in review text.

Exploiting Local and Global Social Context for Recommendation

Empirical results on real-world datasets demonstrate the effectiveness of the proposed framework LOCABAL and further experiments are conducted to understand how local and global social context work for the proposed Framework.