# Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder

arXiv: https://arxiv.org/abs/1607.07514 · HTML: https://mlsanity.com/paper/1607.07514/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2016.

## Built on by (most cited first, 8 of 8)

- [EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition](https://mlsanity.com/paper/2102.03777/) (2021)
- [Recent Trends in Named Entity Recognition (NER)](https://mlsanity.com/paper/2101.11420/) (2021)
- [Geo-Information Harvesting from Social Media Data](https://mlsanity.com/paper/2211.00543/) (2022)
- [NTULM: Enriching Social Media Text Representations with Non-Textual Units](https://mlsanity.com/paper/2210.16586/) (2022)
- [Network representation learning systematic review: ancestors and current development state](https://mlsanity.com/paper/2109.07583/) (2021)
- [Integrating Bidirectional Long Short-Term Memory with Subword Embedding for Authorship Attribution](https://mlsanity.com/paper/2306.14933/) (2023)
- [Detecting Algorithmically Generated Domains Using a GCNN-LSTM Hybrid Neural Network](https://mlsanity.com/paper/2208.03445/) (2022)
- [DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection](https://mlsanity.com/paper/2605.10436/) (2026)

## Abstract (arXiv)

We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model are generic, and hence can be applied to a variety of tasks. Though the model presented in this paper is trained on English-language tweets, the method presented can be used to learn tweet embeddings for different languages.