News texts classification with LSTM recursive neural networks

Description

This project involves classifying news texts into specific categories using an LSTM recursive neural network. The dataset(https://www.kaggle.com/datasets/rmisra/news-category-dataset) contains approximately 210,000 headlines from the Huffpost newspaper spanning the years 2012-2022. The dataset includes various elements, but only the news title and the brief description will be used for identifying the news type. Therefore, we need to preprocess the dataset by removing unnecessary elements. Additionally, text preprocessing and conversion into sequences is required before inputting into the LSTM model. The model's performance is evaluated using the mean absolute error calculation.