Salman Hameed

In the face of exponential growth in research publications, organizing and extracting meaningful insights from vast amounts of scholarly literature has become increasingly challenging. This project aims to address this issue by leveraging Natural Language Processing (NLP) and Machine Learning (ML) techniques.

The project commences with exploratory data analysis (EDA) to gain valuable insights and identify patterns within the research article dataset. Through comprehensive preprocessing, including text cleaning and feature engineering, the data is optimized for subsequent analysis. The dataset is then split into training and testing subsets, and a combination of supervised machine learning and deep learning algorithms is employed for training.

🔍 Exploratory Data Analysis (EDA):
I delve into the dataset, unveiling valuable insights and patterns through visually appealing summaries and statistics.

⚙ Data Preprocessing:
With meticulous preprocessing techniques, I ensure the data is clean and optimized for analysis, enhancing the quality of the results.

🎯 Train, Test, and Evaluate:
By employing a variety of supervised ML and deep learning algorithms, I train models that achieve a remarkable accuracy of 96% on the test dataset.

💾 Model Persistence:
To enable future use and integration, I save the trained models, ensuring their availability for further analysis and applications.

🌐 Flask Real-time Application:
Using Bootstrap and Ajax, I create an intuitive and user-friendly Flask application. Users can input article titles and abstracts, instantly obtaining category predictions. Additionally, batch predictions from uploaded CSV files make it even more convenient.

Let's revolutionize how we organize and analyze research articles together! Feel free to reach out to me for collaboration opportunities or any inquiries you may have. Thanks