Twitter Sentiment Analyser

❤️Inspiration:

The inspiration for this project comes from the increasing use of social media platforms like Twitter and the impact they have on public opinion. Sentiment analysis of tweets can provide valuable insights into public opinion on various topics and help organizations make informed decisions.

What it does?

This project creates a machine learning model for sentiment analysis of tweets. Given a tweet, the model will predict whether the sentiment expressed in the tweet is positive, negative, or neutral.

How we built it?

We built the model using Python and the scikit-learn library. The steps involved in building the model are:

Data Collection: The dataset for this project was collected from Kaggle.

Data Processing: The collected data was pre-processed to remove any unwanted characters and ensure all tweets were in a standard format.

Data Vectorization: The processed tweets were then converted into numerical representations using the bag-of-words model.

Model Training: A machine learning model was trained on the vectorized data to predict the sentiment of tweets. We used the Naive Bayes classifier for this purpose.

Model Evaluation: The trained model was evaluated on a validation dataset to measure its performance.

Challenges we ran into:

One of the biggest challenges we faced was dealing with the large number of missing or incomplete data in the collected dataset. We had to remove these entries to ensure that the model was trained on high-quality data.

Another challenge was dealing with the variability of language in tweets. Tweets often contain slang, abbreviations, and misspelled words, which made pre-processing and vectorization more difficult.

What's next for this project:

In the future, we plan to fine-tune the model by using more advanced techniques such as word embeddings and deep learning. We also plan to extend the model to perform sentiment analysis on other social media platforms like Facebook and Instagram.

Built With

• google-colab
• kaggle
• numpy
• pandas
• scikit-learn