Twitter Sentiment Analysis – NLP
→
Summary
Performed sentiment classification of tweets to identify positive, negative, or neutral opinions using Python on the Sentiment140 dataset, applying various NLP techniques.
About
Highly analytical Bachelor of Technology student specializing in Computer Science with Cyber Security, possessing a robust foundation in Data Science, Machine Learning, and Natural Language Processing. Proven ability to develop and deploy high-accuracy predictive models, demonstrated by achieving 99.96% accuracy in credit card fraud detection and competitive results in sentiment analysis. Eager to leverage expertise in data analysis, machine learning, and problem-solving to contribute to innovative technical challenges within a dynamic technology environment.
Awards
Qualified till Round 2 of national-level coding competition TCS CodeVita
Awarded By
TCS CodeVita
Achieved qualification through the initial rounds of a prestigious national coding competition, demonstrating strong algorithmic and problem-solving skills.
Languages
English
Certificates
NPTEL Cyber Physical System
Issued By
NPTEL
The Bits and Bytes of Computer Networking
Issued By
Coursera (Google)
Data Science Specialization
Issued By
Coursera
AWS Cloud Practitioner Certificate
Issued By
Amazon Web Services (AWS)
Google Data Analytics Professional Certificate
Issued By
Skills
Programming Languages
Python, SQL, Java, C++.
Data Science & Machine Learning
Statistical Analysis, Predictive Modeling, Data Mining, Scikit-learn, TensorFlow, Data Visualization, Matplotlib, Seaborn, Tableau, Power BI.
Data Handling & Tools
Pandas, NumPy, Jupyter Notebook, Excel, Database Management, MySQL, A/B Testing, Exploratory Data Analysis (EDA), Feature Engineering, Data Cleaning.
Natural Language Processing (NLP)
Text Preprocessing, Sentiment Analysis, NLTK.
Deep Learning
Neural Networks, CNN, RNN, Transfer Learning, TensorFlow.
Soft Skills
Critical Thinking, Problem-Solving, Communication, Collaboration, Adaptability.
Projects
Credit Card Fraud Detection – Machine Learning
→
Summary
Developed a machine learning model to detect fraudulent transactions using a dataset of 284,807 entries with 31 features, addressing class imbalance and visualizing results.