Implementation subject: Twitter Sentiment Analysis using deep learning.
DL Model Used : CNN
Accuracy : 97%
Advanced operations: data preprocessing, model creation, parameter adjustment and prediction.
1-Introduction
Emotion analysis is one of the most widely used applications of data science in real-world analysis. Since the world is dependent on social media, users' opinions and explanations can help us understand their feelings and intentions. In this work, I took a dataset from Twitter and I did my best to explain to you all the feelings of users through several modelling techniques and deep acceleration. Network data classifier based on the convolutional neural network. The dataset and its description is available here: https://www.kaggle.com/datasets/saurabhshahane/twitter-sentiment-dataset
Keywords: sentiment analysis , CNN, LSTM, classification and prediction , machine learning , deep learning.
Deep learning may be thought of as a subset of machine learning. This is an area which is based on learning and improving one's own through the examination of computer algorithms. While machine learning uses more straightforward concepts, deep learning works with artificial neural networks, which are designed to mimic the way humans think and learn. Until recently, neural networks were constrained by computational power and therefore by their complexity. However, advances in big data analysis have enabled larger and more sophisticated neural networks, allowing computers to observe, learn and respond to complex situations more quickly than humans. Deep learning facilitated the classification of images, language translation, voice recognition. It may be used to solve any problem of recognition of forms and without human intervention.
Long short-term memory (LSTM) is an artificial recurrent neural network architecture used in the field of deep learning. Contrary to the standard feedforward neural networks, LSTM has feedback connections. It never retains all data as a standard recurring neuronal network, lstm retains short-term memory of the data.
CNN is the most famous and commonly employed algorithm . The main benefit of CNN compared to its predecessors is that it automatically identifies the relevant features without any human supervision . CNNs have been extensively applied in a range of different fields, including computer vision , speech processing , Face Recognition , etc. The structure of CNNs was inspired by neurons in human and animal brains, similar to a conventional neural network. More specifically, in a cat’s brain, a complex sequence of cells forms the visual cortex; this sequence is simulated by the CNN .
Importing Necesaary Packages and Libraries:
pip install gensim --upgrade
pip install keras --upgrade
pip install pandas --upgrade
I prefer working with anaconda
References
CNN Overview: https://link.springer.com/article/10.1186/s40537-021-00444-8
LSTM Overview : https://www.analyticsvidhya.com/blog/2022/03/an-overview-on-long-short-term-memory-lstm/
Code Optimisation Techniques :https://www.geeksforgeeks.org/optimization-tips-python-code/