Research Articles Analysis using NLP Techniques

[atharv1707]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : NLP on Research Articles :red_circle: Aim : Given the abstract and title for a set of research articles, predict the topics for each article included in the test set. :red_circle: Dataset : https://www.kaggle.com/datasets/vetrirah/janatahack-independence-day-2020-ml-hackathon/data :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 :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Atharv Pal
• GitHub Profile Link : https://github.com/atharv1707
• Email ID :
• Participant ID (if applicable):
• Approach for this Project : I'll start with dataset preprocessing, and performing EDA to understand the distribution of the dataset. After cleaning, and processing the dataset into a format fit for my approach, I plan to choose SciBERT to convert the titles and abstracts into embeddings, which can help because similar texts will have similar embeddings, which is crucial for the classification task. This being done, I will feed the processed data into a MLP to predict presence of 0/1 as per the dataset. Finally, we will evaluate the performance on metrics like accuracy and F1 score.
• What is your participant role? (Mention the Open Source program) GSSoC'24 Contributor

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

You are planning to implement SciBERT, along with that what are the other models you are planning to implement here?

[DebanKsahu]

Full name : Deban Kumar Sahu GitHub Profile Link : https://github.com/DebanKsahu Email ID : [email protected] Participant ID (if applicable): Approach for this Project : I looked into the dataset that contains 2 important features from which we can predict which topic is this text, so it's giving me a hint to use a multi input model where one input will be abstract and other one will be title and at the end you will have to predict final results. For text processing I will use basic python text methods . I will start with building my own model witch contains LSTM,conv1D,BiLSTM,GRU and fine tuning the hyper parameters with the help of keras-tunner which use random search. Then I will use pre trained embedding like universal sentence encoder to increase the accuracy. participant role;-GSSoC'24 Extd Contributor

[abhisheks008]

Hi @DebanKsahu thanks for sharing your approach. You can start working on it.

Assigned to you.