# Word2Vec applied to Recommendation: Hyperparameters Matter

arXiv: https://arxiv.org/abs/1804.04212 · HTML: https://mlsanity.com/paper/1804.04212/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2018.

## Built on by (most cited first, 20 of 20)

- [Contrastive language and vision learning of general fashion concepts](https://mlsanity.com/paper/2204.03972/) (2022)
- [On the Theories Behind Hard Negative Sampling for Recommendation](https://mlsanity.com/paper/2302.03472/) (2023)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Model Selection for Generic Contextual Bandits](https://mlsanity.com/paper/2107.03455/) (2021)
- [Enhancing Cognitive Diagnosis using Un-interacted Exercises: A Collaboration-aware Mixed Sampling Approach](https://mlsanity.com/paper/2312.10110/) (2023)
- [Pitchclass2vec: Symbolic Music Structure Segmentation with Chord Embeddings](https://mlsanity.com/paper/2303.15306/) (2023)
- [ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code](https://mlsanity.com/paper/2411.16927/) (2024)
- [Deep Learning-based Online Alternative Product Recommendations at Scale](https://mlsanity.com/paper/2104.07572/) (2021)
- [One System to Rule them All: a Universal Intent Recognition System for Customer Service Chatbots](https://mlsanity.com/paper/2112.08261/) (2021)
- [Two Is Better Than One: Dual Embeddings for Complementary Product Recommendations](https://mlsanity.com/paper/2211.14982/) (2022)
- [Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation](https://mlsanity.com/paper/2301.07483/) (2023)
- [Knowledge Enhanced Graph Neural Networks for Graph Completion](https://mlsanity.com/paper/2303.15487/) (2023)
- [Bayesian Negative Sampling for Recommendation](https://mlsanity.com/paper/2204.06520/) (2022)
- [Of Spiky SVDs and Music Recommendation](https://mlsanity.com/paper/2307.01212/) (2023)
- [Personalized Negative Reservoir for Incremental Learning in Recommender Systems](https://mlsanity.com/paper/2403.03993/) (2024)
- [Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems](https://mlsanity.com/paper/2506.22648/) (2025)
- [Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Model](https://mlsanity.com/paper/2203.15595/) (2022)
- [Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction](https://mlsanity.com/paper/2312.04815/) (2023)
- [Beyond Models! Explainable Data Valuation and Metric Adaption for Recommendation](https://mlsanity.com/paper/2502.08685/) (2025)
- [IntSR: An Integrated Generative Framework for Search and Recommendation](https://mlsanity.com/paper/2509.21179/) (2025)

## Abstract (arXiv)

Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the same tasks, recommendation applications tend to use the same already tuned hyperparameters values, even if optimal hyperparameters values are often known to be data and task dependent. We thus investigate the marginal importance of each hyperparameter in a recommendation setting through large hyperparameter grid searches on various datasets. Results reveal that optimizing neglected hyperparameters, namely negative sampling distribution, number of epochs, subsampling parameter and window-size, significantly improves performance on a recommendation task, and can increase it by an order of magnitude. Importantly, we find that optimal hyperparameters configurations for Natural Language Processing tasks and Recommendation tasks are noticeably different.