# The Document Vectors Using Cosine Similarity Revisited

arXiv: https://arxiv.org/abs/2205.13357 · HTML: https://mlsanity.com/paper/2205.13357/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 8 of 8)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method](https://mlsanity.com/paper/1402.3722/) (2014)
- [Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews](https://mlsanity.com/paper/1412.5335/) (2014)
- [Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews](https://mlsanity.com/paper/1512.08183/) (2015)

## Built on by (most cited first, 5 of 5)

- [Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment](https://mlsanity.com/paper/2206.08614/) (2022)
- [This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish](https://mlsanity.com/paper/2211.13112/) (2022)
- [Fine-tuning BERT with Bidirectional LSTM for Fine-grained Movie Reviews Sentiment Analysis](https://mlsanity.com/paper/2502.20682/) (2025)
- [QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking](https://mlsanity.com/paper/2510.11589/) (2025)
- [SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2605.23440/) (2026)

## Abstract (arXiv)

The current state-of-the-art test accuracy (97.42%) on the IMDB movie reviews dataset was reported by citetthongtan-phienthrakul-2019-sentiment and achieved by the logistic regression classifier trained on the Document Vectors using Cosine Similarity (DV-ngrams-cosine) proposed in their paper and the Bag-of-N-grams (BON) vectors scaled by Naive Bayesian weights. While large pre-trained Transformer-based models have shown SOTA results across many datasets and tasks, the aforementioned model has not been surpassed by them, despite being much simpler and pre-trained on the IMDB dataset only. In this paper, we describe an error in the evaluation procedure of this model, which was found when we were trying to analyze its excellent performance on the IMDB dataset. We further show that the previously reported test accuracy of 97.42% is invalid and should be corrected to 93.68%. We also analyze the model performance with different amounts of training data (subsets of the IMDB dataset) and compare it to the Transformer-based RoBERTa model. The results show that while RoBERTa has a clear advantage for larger training sets, the DV-ngrams-cosine performs better than RoBERTa when the labelled training set is very small (10 or 20 documents). Finally, we introduce a sub-sampling scheme based on Naive Bayesian weights for the training process of the DV-ngrams-cosine, which leads to faster training and better quality.