Chill's Data Blog

  In my journey to develop a sentiment analysis tool, and from my participation in past machine learning assignments, I've discovered the importance of leveraging powerful hardware to handle the intensive computations required by deep learning models. One such powerful tool is CUDA, a parallel computing platform and API model created by NVIDIA.  Activating CUDA GPU processing on a recent project drastically reduced the time taken to train one of my models from well over an hour to just shy of 5 minutes! It was at this very moment my fascination with all things CUDA was born. Want to understand how it all works? Continue reading! What is NVIDIA CUDA? NVIDIA CUDA (Compute Unified Device Architecture) is a parallel computing platform and programming model that enables developers to harness the power of NVIDIA GPUs for general-purpose computing. CUDA allows developers to write software that executes multiple tasks simultaneously in parallel, taking advantage of the thousands of co...

In my previous posts, I discussed the goal of developing a sentiment analysis tool and the methodologies I intend to use. Now its time to discuss the tools and techniques I'll be relying on to make bring this project to life. From data collection to model deployment, each stage of the project requires specialised software and libraries to steer it to completion. Data collection will be taken care of with the help of  BeautifulSoup and Scrapy : These libraries are used for web scraping, which will help me gather data from other social media platforms and websites. BeautifulSoup is great for parsing HTML and XML documents, while Scrapy is a very capable framework for large-scale web scraping (Stsiopkina, 2024 ). Preprocessing will be completed primarily with   NLTK (Natural Language Toolkit) and  spaCy.  NLTK is a  comprehensive library is used for various NLP tasks such as tokenisation, lemmatisation, and stemming. It’s a staple in the NLP community and provides ...

When tackling a research project solo, especially with a tight three-month deadline, effective time management and organisation are essential. While Agile methodology is highly effective for team projects, managing it solo can be quite challenging due to its iterative nature and the need for constant communication and feedback loops. For my sentiment analysis project, I have deemed Kanban boards  (a framework which actually falls under the Agile umbrella), to be a more practical approach to project management. Let me explain why... Why Kanban Boards? Kanban is a visual project management tool that helps track tasks and manage workflow efficiently. It’s particularly well-suited for solo projects because it provides clear visibility into what needs to be done, what is in progress, and what is completed. Here’s why Kanban is the best fit for my project: Visual Workflow Management : Kanban boards use visual cards to represent tasks, making it easy to see the status of each task at a gl...

  As my research continues, it's becoming all the more apparent just how vital Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory networks (LSTMs) are, within the context of my project. Each offer unique strengths that make them particularly useful for natural language processing tasks like sentiment analysis. Below is a breakdown what each of these models is and why they are important for this project. Convolutional Neural Networks (CNNs) CNNs are a type of deep learning model initially designed for image processing. They excel at recognising patterns and features in data through the use of convolutional layers that apply filters to the input data. There are several reasons why CNNs are useful for sentiment analysis, including: Local Feature Detection : CNNs are adept at identifying local patterns in text, such as the presence of specific words or phrases that can indicate sentiment. This capability is crucial for understanding the c...

In my previous post, I introduced the goal of developing an advanced sentiment analysis tool tailored for social media. Now, let's dive deeper into the research questions driving this project and the methodologies I'll use to answer them. Formulating the right questions is crucial, as it sets the direction for the entire research process. Using a mix of quantitative and qualitative methods allows for a more comprehensive understanding and ensures robust outcomes. The core of any research project lies in its questions. For this sentiment analysis tool, I've identified three main questions that will guide my research: How can sentiment analysis tools more accurately identify and categorise emotions in social media texts? What are the most effective machine learning algorithms and NLP techniques for improving sentiment analysis accuracy, including the detection of nuances including sarcasm and irony? How can the design of this tool be optimised for user accessibility and inter...

Social media has become a central hub for public discourse, impacting everything from business strategies to political campaigns (Kaplan & Haenlein, 2010). The vast amount of user-generated content on these platforms offers a goldmine of data that, when analysed, can reveal valuable insights into public sentiment. This is where sentiment analysis comes in, aiming to extract subjective information from text to understand what people are thinking and feeling (Shamsi, Bayari & Salloum, 2021). My research project is all about developing a smart sentiment analysis tool designed specifically for social media. The tool will combine advanced Natural Language Processing (NLP) techniques with cutting-edge machine learning algorithms to accurately analyse and categorise the emotional tone of social media posts. Traditional sentiment analysis tools often miss the mark when it comes to capturing the nuances of social media language—things like sarcasm, slang, and context-specific expressio...