Pranitha bokketi

Dynamic Assistant Manager at Streenidhi Credit Cooperative Ltd, adept at enhancing financial accessibility through effective loan disbursement and strategic credit recovery. Proven ability in financial analysis and customer relations, driving operational success across multiple mandals while leveraging data management skills to optimize processes and improve outcomes. Motivated professional with several years of experience juggling multiple priorities to keep company running smoothly.

After getting married, I resigned from my job and took a one-year break. During this time, I dedicated myself to learning machine learning and completing various projects. Now, I am actively seeking a data science job.

• I was awarded the Malsar Sudoku Championship title in 2023!

OBJECTIVE:

The primary objective of this project is to develop a machine learning model capable of accurately classifying news articles as either 'real' or 'fake.' This aims to combat the spread of misinformation and promote informed decision-making.

METHODOLOGY:

1. Data collection and preprocessing: A dataset of news articles labeled as 'real' or 'fake' will be collected, and textual data will be cleaned, removing irrelevant characters and stop words, stemming, and converting to lowercase

2. Feature extraction: Key features such as writing style, sentiment, source credibility, and specific keywords will be identified, and text data will be transformed into numerical vectors using techniques like TF-IDF, creating a feature representation for each article

3. Model training and evaluation: A suitable machine learning model, such as logistic regression, naive Bayes, or support vector machines, will be selected. The model will be trained using the labeled dataset, and its performance will be evaluated using metrics like accuracy, precision, recall, and F1 score

4. Prediction: The trained model will be used to predict the authenticity of new, unseen news articles, providing a classification of "real" or "fake"

CONCLUSION:

By leveraging machine learning algorithms and carefully engineered features, the project aims to develop a robust and accurate the fake news detection system. The model's performance will be assessed using various evaluation metrics, and potential improvements or limitations will be identified. The developed system has the potential to assist users in identifying fake news and promote a more informed online environment.