Open abhisheks008 opened 1 year ago
Please inform the approach of your project. And also finish the last pull request, I have requested some changes there. After that this issue will be assigned to you.
@Abhinavcode13
Full name : Soumyadeep Das GitHub Profile Link : https://github.com/soumyadeepdas28 Email ID : soumyadeepdas295@gmail.com Participant ID (if applicable): Approach for this Project : Using NLP and Deep learning using Tensorflow What is your participant role? (Mention the Open Source program) : SSOC 2.0
Full name : NANCY SRIVASTAVA GitHub Profile Link : https://github.com/Nansri108 Email ID : srivastavanancy55@gmail.com Participant ID (if applicable): Approach for this Project : Using NLP and Deep learning using Tensorflow and I do lot more which is possible in it. What is your participant role? (Mention the Open Source program) : SSOC 2.0
@soumyadeepdas28 and @Nansri108 can you please confirm me the exact models you are going to use here as you have to prepare at least 3 deep learning models for this particular project.
@abhisheks008 I will use pre-trained models like tensorflow bert and will create an ANN Model and also pickup one pre-trained model from Hugging Face
@Nansri108 what will be your approach for solving this?
@abhisheks008 hello, Can you assign me so I can begin ASAP?If not , please let me know
Issue assigned to you @soumyadeepdas28
@abhisheks008 Thanks you for assigning me to the project
@abhisheks008 , Can I use another dataset for this project?
Yeah sure. If it is providing better results than the given one, then go for it. Make sure you mention the dataset source/URL in your project.
Full name : Utkarsh Trivedi GitHub Profile Link : https://github.com/UtkarshTrivedi2934 Email ID : 21053223@kiit.ac.in Participant ID (if applicable): Approach for this Project : To classify cyberbullying using NLP, collecting a dataset, preprocess text data, use techniques like TF-IDF or word embeddings, choosing a suitable model, train and evaluate. Regularly monitor and update the model for ongoing effectiveness. What is your participant role? (Mention the Open Source program) : SWOC season 4
Issue assigned to you @UtkarshTrivedi2934
Issue assigned to you @UtkarshTrivedi2934
Hey, can I use a different dataset, like the one below? [Uploading Cyberbullying_Dataset.csv…]()
Which dataset you wanna use, can you share the URL? @UtkarshTrivedi2934
Which dataset you wanna use, can you share the URL? @UtkarshTrivedi2934
Kindly find the URL below: https://github.com/mrizwanakram/CyberBulling-With-Machine_Learning/blob/main/Cyberbullying_Dataset.csv
It will be better if you use the Kaggle resource here, that will help others to generalize their views. If you find the Kaggle URL of the above dataset, do share that here.
It will be better if you use the Kaggle resource here, that will help others to generalize their views. If you find the Kaggle URL of the above dataset, do share that here.
It will be better if you use the Kaggle resource here, that will help others to generalize their views. If you find the Kaggle URL of the above dataset, do share that here.
Actually the thing is Im uable to interpret the input and output from the given dataset, could you please help me with that?
Can you find out the dataset of your choice from Kaggle?
Can you find out the dataset of your choice from Kaggle? Yea, I found one. Have a look https://www.kaggle.com/code/chandrug/cyperpulling-detection/input So basically its a JSON file, which I'll convert to CSV and then use it.
You can go ahead with it. I have updated the dataset with the new one in the issue details.
You can go ahead with it. I have updated the dataset with the new one in the issue details.
thanks a lot, abhishek.
Full name : Aindree Chatterjee
GitHub Profile Link : https://github.com/aindree2005
Email ID : aindree2005@gmail.com
Participant ID (if applicable):
Approach for this Project : Trying using Bi-LSTM, BERT , and Naive Bayes Classifier
What is your participant role? (Mention the Open Source program) : GSSOC 2024
@abhisheks008 can I work on this?
Full name : Aindree Chatterjee GitHub Profile Link : https://github.com/aindree2005 Email ID : aindree2005@gmail.com Participant ID (if applicable): Approach for this Project : Trying using Bi-LSTM, BERT , and Naive Bayes Classifier What is your participant role? (Mention the Open Source program) :
GSSOC 2024
@abhisheks008 can I work on this?
Assigned to you @aindree-2005. Are you up with the web app too?
Full name : Aindree Chatterjee GitHub Profile Link : https://github.com/aindree2005 Email ID : aindree2005@gmail.com Participant ID (if applicable): Approach for this Project : Trying using Bi-LSTM, BERT , and Naive Bayes Classifier What is your participant role? (Mention the Open Source program) :
GSSOC 2024
@abhisheks008 can I work on this?Assigned to you @aindree-2005. Are you up with the web app too?
Sure I can try to make the web app, maybe once the model is done, I can do a separate PR for the app , under this issue?
Full name : Aindree Chatterjee GitHub Profile Link : https://github.com/aindree2005 Email ID : aindree2005@gmail.com Participant ID (if applicable): Approach for this Project : Trying using Bi-LSTM, BERT , and Naive Bayes Classifier What is your participant role? (Mention the Open Source program) :
GSSOC 2024
@abhisheks008 can I work on this?Assigned to you @aindree-2005. Are you up with the web app too?
Sure I can try to make the web app, maybe once the model is done, I can do a separate PR for the app , under this issue?
Cool no issues, for the web app I'll create a new issue once you are done with this.
Deep Learning Simplified Repository (Proposing new issue)
:red_circle: Project Title : Classification of Cyber Bulling using NLP :red_circle: Aim : Create a classification model based on the given dataset using NLP. :red_circle: Dataset : https://www.kaggle.com/code/chandrug/cyperpulling-detection/input :red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.
📍 Follow the Guidelines to Contribute in the Project :
requirements.txt
- This file will contain the required packages/libraries to run the project in other machines.Model
folder, theREADME.md
file must be filled up properly, with proper visualizations and conclusions.:red_circle::yellow_circle: Points to Note :
:white_check_mark: To be Mentioned while taking the issue :
Happy Contributing 🚀
All the best. Enjoy your open source journey ahead. 😎