What question did this study set out to answer?

To develop an explainable user-based collaborative recommendation framework that combines clustering, similarity metrics, and generative language models to improve recommendation transparency in social media.

September 17, 2026InformaticsOpen Access

An Explainable Collaborative Recommendation Framework Using K-Means Clustering and LLM-Based Explanations

View Full Paper

Ask AI

Bookmark

Authors

AAAmjad Alaskar EAEman Alasmari DADimah Alahmadi

Discussion

Member takes

Overview

Algorithm development study demonstrates high similarity and clear explanations for social media recommendations, highlighting improved system transparency.

Key Points

To develop an explainable user-based collaborative recommendation framework that combines clustering, similarity metrics, and generative language models to improve recommendation transparency in social media.
Clustered users by behavioral traits using K-Means clustering and selected Top-N similar peers via Pearson and Cosine similarity metrics.
Generated content theme and content type recommendations using similarity-based neighbor voting.
Integrated the Gemini 2.5 Flash language model to construct brief, human-readable explanations for recommended items.
Demonstrated strong behavioral similarity among adjacent users, achieving a Mean Pearson Similarity of 0.8044, Mean Cosine Similarity of 0.8113, and Mean Combined Similarity of 0.8078.
Content-type recommendations outperformed preferred-theme recommendations in social media environments with high content volume.

Cite This Study

Alaskar et al. (2026) studied this question.

synapsesocial.com/papers/6aabb6725f706d05830e4f37 https://doi.org/10.3390/informatics13090150

View Full Paper

Ask AI

Bookmark

September 17, 2026InformaticsOpen Access

An Explainable Collaborative Recommendation Framework Using K-Means Clustering and LLM-Based Explanations

View Full Paper

Ask AI

Bookmark

Authors

AAAmjad Alaskar EAEman Alasmari DADimah Alahmadi

Discussion

Member takes

Overview

Algorithm development study demonstrates high similarity and clear explanations for social media recommendations, highlighting improved system transparency.

Key Points

To develop an explainable user-based collaborative recommendation framework that combines clustering, similarity metrics, and generative language models to improve recommendation transparency in social media.
Clustered users by behavioral traits using K-Means clustering and selected Top-N similar peers via Pearson and Cosine similarity metrics.
Generated content theme and content type recommendations using similarity-based neighbor voting.
Integrated the Gemini 2.5 Flash language model to construct brief, human-readable explanations for recommended items.
Demonstrated strong behavioral similarity among adjacent users, achieving a Mean Pearson Similarity of 0.8044, Mean Cosine Similarity of 0.8113, and Mean Combined Similarity of 0.8078.
Content-type recommendations outperformed preferred-theme recommendations in social media environments with high content volume.

Cite This Study

Alaskar et al. (2026) studied this question.

synapsesocial.com/papers/6aabb6725f706d05830e4f37 https://doi.org/10.3390/informatics13090150

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark