Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
Name
tweet2vec_vvr.pdf
Description
Main article
Size
646.35 KB
Format
Adobe PDF
Checksum (MD5)
6ef6640ab1e18579c14510bba3c88468
Author(s)
Vosoughi, Soroush
Vijayaraghavan, Prashanth
Roy, Deb K
Date Issued
July 2016
Journal
Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '16
Publisher
Association for Computing Machinery (ACM)
Citation
Vosoughi, Soroush, Prashanth Vijayaraghavan, and Deb Roy. "Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder." Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR ’16, July 17-21, 2016, Pisa, Italy.
Version
Author's final manuscript
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/2911451.2914762
