Hate speech detection from social networking posts using CNN and XGBoost
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.
| Päätekijät: | , , , |
|---|---|
| Muut tekijät: | |
| Aineistotyyppi: | Opinnäyte |
| Kieli: | en_US |
| Julkaistu: |
Brac University
2020
|
| Aiheet: | |
| Linkit: | http://hdl.handle.net/10361/14057 |
| id |
10361-14057 |
|---|---|
| record_format |
dspace |
| spelling |
10361-140572022-01-26T10:08:22Z Hate speech detection from social networking posts using CNN and XGBoost Shahadat, Ashraf Bin Rony, Md. Mizanur Rahman Anwar, Md. Adnanul Joy, Eialid Ahmed Alam, Md. Golam Rabiul Department of Computer Science and Engineering, Brac University Natural Language processing Hatespeech Offensive Language Convolutional Neural Network(CNN) XGBoost This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019. Cataloged from PDF version of thesis. Includes bibliographical references (pages 62-65). The increasing growth of social networks and microblogging websites have enabled people from different backgrounds and diverse moral codes to communicate with each other quite easily. While social media promotes communication and sharing of information, these are also used to initiate heinous and negative campaigns. Social networks although discourage such act but people often use these social platforms to propagate offensive and hatred towards individuals or specific groups. Therefore,detecting hate speech has become a serious issue that needs considerable attention. The goal of this research is to detect such campaigns of hate. In this paper, two different approaches have been proposed for detecting hate and offensive language on social platforms. The paper proposes Natural language processing with CNN architecture and XGBoost classifier which will be explicitly effective for capturing the context and the semantics of hate speech. The proposed classifiers distinguish hate speech from neutral text and can achieve a higher quality of classification than current state-of-the-art algorithms.Using CNN,the accuracy that has been obtained on detecting if a tweet is offensive or neutral is 89.18% and on another datasetcontaining hateful, offensive and neutral comments, the accuracy is 84.74%.The later approach of using XGBoost classifier has achieved an accuracy of 93.10% and 80.51% respectively.In addition,2333 tweets have been collected from twitter and labelled using annotators.On that dataset, using CNN model the accuracy is 76.70% and for XGBoost the accuracy is 78.14%. Ashraf Bin Shahadat Md. Mizanur Rahman Rony Md. Adnanul Anwar Eialid Ahmed Joy B. Computer Science 2020-10-12T06:16:45Z 2020-10-12T06:16:45Z 2019 2019-12 Thesis ID: 16101199 ID: 16101184 ID: 16101005 ID: 16101182 http://hdl.handle.net/10361/14057 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 65 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Natural Language processing Hatespeech Offensive Language Convolutional Neural Network(CNN) XGBoost |
| spellingShingle |
Natural Language processing Hatespeech Offensive Language Convolutional Neural Network(CNN) XGBoost Shahadat, Ashraf Bin Rony, Md. Mizanur Rahman Anwar, Md. Adnanul Joy, Eialid Ahmed Hate speech detection from social networking posts using CNN and XGBoost |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019. |
| author2 |
Alam, Md. Golam Rabiul |
| author_facet |
Alam, Md. Golam Rabiul Shahadat, Ashraf Bin Rony, Md. Mizanur Rahman Anwar, Md. Adnanul Joy, Eialid Ahmed |
| format |
Thesis |
| author |
Shahadat, Ashraf Bin Rony, Md. Mizanur Rahman Anwar, Md. Adnanul Joy, Eialid Ahmed |
| author_sort |
Shahadat, Ashraf Bin |
| title |
Hate speech detection from social networking posts using CNN and XGBoost |
| title_short |
Hate speech detection from social networking posts using CNN and XGBoost |
| title_full |
Hate speech detection from social networking posts using CNN and XGBoost |
| title_fullStr |
Hate speech detection from social networking posts using CNN and XGBoost |
| title_full_unstemmed |
Hate speech detection from social networking posts using CNN and XGBoost |
| title_sort |
hate speech detection from social networking posts using cnn and xgboost |
| publisher |
Brac University |
| publishDate |
2020 |
| url |
http://hdl.handle.net/10361/14057 |
| work_keys_str_mv |
AT shahadatashrafbin hatespeechdetectionfromsocialnetworkingpostsusingcnnandxgboost AT ronymdmizanurrahman hatespeechdetectionfromsocialnetworkingpostsusingcnnandxgboost AT anwarmdadnanul hatespeechdetectionfromsocialnetworkingpostsusingcnnandxgboost AT joyeialidahmed hatespeechdetectionfromsocialnetworkingpostsusingcnnandxgboost |
| _version_ |
1814307417542885376 |