Deerwalk

JOURNAL OF COMPUTER SCIENCE & TECHNOLOGY



Automated Detection of Hate Speech in Twitter Using Natural Language Processing

Aayam Ojha

Keywords: NLP, Hate Speech Classification, SVM, NLP Classifier, LSTM, Chrome Extension

Published Date: 2024-09-09

This research project aimed to develop a highly efficient and effective Chrome extension 
that could classify tweets containing hate speech, along with conducting sentiment and 
topic analysis. Hate speech is a persistent and concerning issue on Twitter, yet the platform 
has made little effort to address it. To address this challenge, this research performed a 
series of experiments, including the use of Support Vector Machine (SVM), Random 
Forest, and Long Short-Term Memory-based (LSTM) neural network classifiers. The 
results of the experiments showed that the SVM classifier, combined with word2vec [1] 
feature engineering, outperformed all other methods. 
Then developed the Chrome extension using a monolithic repository architecture, utilizing 
React and Django. By implementing this extension, users are able to automatically analyze 
live tweets and identify hate speech content, along with obtaining sentiment and topic 
analysis. The outcome of this research project could provide a significant contribution 
towards a more positive online environment and towards curbing the prevalence of hate 
speech on Twitter.

Prediction of Stock Trading Action using Generative Adversarial Network in Nepali Stock Market

Pranav Dahal

Keywords: Stock Prediction; Technical Analysis; GAN Model; Stock Trading

Published Date: 2024-09-09

Can deep learning approaches achieve similar accuracy as statistical models in predicting 
the stock market? This research introduces an approach integrating Generative Adversarial 
Networks (GANs) with Long Short-Term Memory (LSTM) generators and Convolutional 
Neural Network (CNN) discriminators to predict stock trading actions. By analyzing and 
computing on historical Open, High, Low, Close and Volume (OHLCV) data of the stock 
market, we generate a wide range of input features using Fourier transforms, auto-encoders, 
and several technical indicators. Extreme Gradient Boosting (XGBoost) is employed to 
filter and extract important features. The extracted features are fed into the LSTM 
generator, whose output is then fed to the CNN discriminator to discriminate the buy, sell, 
or hold signals. Results demonstrate the model's effectiveness in capturing temporal and 
spatial patterns, with implications for refining stock trading strategies and enhancing 
financial decision-making for maximizing profits.

Illuminating the Impact of Diverse Lighting Environments on Barley Plant Photosynthesis

Madhu Sudhan Bhusal, Nishant Adhikari, Paurakh Raj Pandey, Sagina Maharjan,, Yawat Malla

Keywords: Photosynthetic Reaction Centers, Photosynthetically Active Radiation, Bose-Einstein condensate, Electron Transfer, Barley

Published Date: 2024-09-09

Convolutional Neural Networks for Fashion Classification

Anuska Basnet, Muskan Singh, Saishab Bhattarai, Simone Shree Pathak

Keywords: Convolutional Neural Networks, Fashion Advisor, Machine Learning, Data Collection.

Published Date: 2024-09-09

SOCKETDB: DBMS WITH DATA STREAMING VIA WEBSOCKETS

Abhinav Gyawali

Keywords: Database; DBMS; WebSockets; SQL; storage; relational algebra

Published Date: 2024-09-10