binar_goldchallenge
Science Score: 18.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: BagasHada
- Language: Python
- Default Branch: main
- Size: 1.25 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
id-multi-label-hate-speech-and-abusive-language-detection
About this data
Here we provide our dataset for multi-label hate speech and abusive language detection in the Indonesian Twitter. The main dataset can be seen at re_dataset with labels information as follows: * HS : hate speech label; * Abusive : abusive language label; * HS_Individual : hate speech targeted to an individual; * HS_Group : hate speech targeted to a group; * HS_Religion : hate speech related to religion/creed; * HS_Race : hate speech related to race/ethnicity; * HS_Physical : hate speech related to physical/disability; * HS_Gender : hate speech related to gender/sexual orientation; * HS_Gender : hate related to other invective/slander; * HS_Weak : weak hate speech; * HS_Moderate : moderate hate speech; * HS_Strong : strong hate speech.
For each label, 1 means yes (tweets including that label), 0 mean no (tweets are not included in that label).
Due to the Twitter's Terms of Service, we do not provide the tweet ID. All username and URL in this dataset are changed into USER and URL.
For text normalization in our experiment, we built typo and slang words dictionaries named new_kamusalay.csv, that contain two columns (first columns are the typo and slang words, and the second one is the formal words). Here the examples of mapping: * beud --> banget * jgn --> jangan * loe --> kamu
Furthermore, we also built abusive lexicon list named abusive.csv that can be used for feature extraction.
More detail
If you want to know how this dataset was build (include the explanation of crawling and annotation technique) and how we did our experiment in multi-label hate speech and abusive language detection in Indonesian language using this dataset, you can read our paper in here: https://www.aclweb.org/anthology/W19-3506.pdf.
How to cite us
This dataset and the other resource can be used for free, but if you want to publish paper/publication using this dataset, please cite this publication:
Muhammad Okky Ibrohim and Indra Budi. 2019. Multi-label Hate Speech and Abusive Language Detection in Indonesian Twitter. In ALW3: 3rd Workshop on Abusive Language Online, 46-57. (Every paper template may have different citation writting. For LaTex user, you can see citation.bib).
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Binar_GoldChallenge
Owner
- Name: Bagas Hada
- Login: BagasHada
- Kind: user
- Repositories: 1
- Profile: https://github.com/BagasHada
Hallo, my name is Bagas, I have a Bachelor' degree in Industrial Engineering.
Citation (citation.bib)
@inproceedings{ibrohim-budi-2019-multi,
title = "Multi-label Hate Speech and Abusive Language Detection in {I}ndonesian Twitter",
author = "Ibrohim, Muhammad Okky and
Budi, Indra",
booktitle = "Proceedings of the Third Workshop on Abusive Language Online",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/W19-3506",
doi = "10.18653/v1/W19-3506",
pages = "46--57",
abstract = "Hate speech and abusive language spreading on social media need to be detected automatically to avoid conflict between citizen. Moreover, hate speech has a target, category, and level that also needs to be detected to help the authority in prioritizing which hate speech must be addressed immediately. This research discusses multi-label text classification for abusive language and hate speech detection including detecting the target, category, and level of hate speech in Indonesian Twitter using machine learning approach with Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest Decision Tree (RFDT) classifier and Binary Relevance (BR), Label Power-set (LP), and Classifier Chains (CC) as the data transformation method. We used several kinds of feature extractions which are term frequency, orthography, and lexicon features. Our experiment results show that in general RFDT classifier using LP as the transformation method gives the best accuracy with fast computational time.",
}