Draft implementation for our SIGIR 2017 paper : "Multitask Learning for Fine-Grained Twitter Sentiment Analysis". If you find this code useful in your research, please consider citing:
@inproceedings{Balikas:2017:MLF:3077136.3080702,
author = {Balikas, Georgios and Moura, Simon and Amini, Massih-Reza},
title = {Multitask Learning for Fine-Grained Twitter Sentiment Analysis},
booktitle = {Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval},
series = {SIGIR '17},
year = {2017},
isbn = {978-1-4503-5022-8},
location = {Shinjuku, Tokyo, Japan},
pages = {1005--1008},
numpages = {4},
url = {http://doi.acm.org/10.1145/3077136.3080702},
doi = {10.1145/3077136.3080702},
acmid = {3080702},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {bilstm, deep learning, multitask learning, sentiment analysis, text classification, text mining, twitter analysis},
}