Social Media IE

Social Media information extraction tool. It supports the following tasks:

Sequence Tagging: Named Entity Recognition, Part of Speech, Chunking, CCG Supersense Tagging (List of datasets at: https://socialmediaie.github.io/datasets.html
Classification: Sentiment classification, Abusive Speech Classification, Uncertainity indicator classification
Active Learning: Classification tasks using active learning

Tutorial on using SocialMediaIE can be found at our IC2S2 2020 tutorial website

Please cite the following if using the tool:

Shubhanshu Mishra. 2019. Multi-dataset-multi-task Neural Sequence Tagging for Information Extraction from Tweets. In Proceedings of the 30th ACM Conference on Hypertext and Social Media (HT '19). ACM, New York, NY, USA, 283-284. DOI: https://doi.org/10.1145/3342220.3344929
Shubhanshu Mishra. 2019. Information extraction from digital social trace data with applications to social media and scholarly communication data. PhD Dissertation, University of Illinois at Urbana-Champaign. https://shubhanshu.com/phd_thesis/

Pretrained multi-task models and experimental models

Mishra, Shubhanshu (2019): Trained models for multi-task multi-dataset learning for text classification as well as sequence tagging in tweets. University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-1094364_V1
Mishra, Shubhanshu (2019): Trained models for multi-task multi-dataset learning for text classification in tweets. University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-1917934_V1
Mishra, Shubhanshu (2019): Trained models for multi-task multi-dataset learning for sequence prediction in tweets. University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-0934773_V1

Main library for doing the analyis

Example applications of the library and additional experiments

Run experiments based on dataset

Install in editable mode:

pip install -e .

Install as pip package:

pip install .

https://samnicholls.net/2016/06/15/how-to-sphinx-readthedocs/

cd docs/
sphinx-apidoc -o source/ ../SocialMediaIE

python -m ipykernel install --user --name ${CONDA_DEFAULT_ENV} --display-name "Python (${CONDA_DEFAULT_ENV})"

This library builds upon AllenNLP and Pytorch. Some of the mutli-task learning code is based on the multi-task learning examples in allennlp.