Inspiration
So Basically as an undergrad student who is developing skills for upscaling my career. I inspired the project while I'm learning ml and data analytics and working on it, and then I thought about how WhatsApp improved its messaging application for the next features because the user plays the main role, so that's what I got inspired in making this project.
What it does
So Whatsapp chat analysis does collecting of data in the chat and classifies it into different sections which makes easy how users respond in various whether it's texting who'll be online more what are time graphs, heat maps, or bar charts. how many messages go through all things like links, and emotes, it's a basic version I didn't implement the media and other text formats . Can be improvised throughout in future
How I built it
So Basically not going directly through the application,I tested out how the data of WhatsApp text converted and adding other libraries first in Jupyter, Then I went through adding whole data then using Streamlit as the main library of data science/analytics application i developed preprocessing of data,add a connection through helper where other data will be available the whole architecture of connects to main applications. For Classifying the main data libraries used streamlit,pandas,urlextract,matplotlib ,wordcloud, and emoji. then for dataset, i created words from two languages hind & English.after all completion we need to download chat data in text from WhatsApp,then upload it &it will analyse the whole data
challenges
The challenges that you have faced in this project include: The data is noisy and unstructured.The task of sentiment analysis is challenging, as it requires understanding the context of messages.The machine learning model is not very accurate.
Accomplished
You developed a Python script that can extract data from WhatsApp chat logs. This is a significant accomplishment, as it allows you to access and analyze a large amount of data that would otherwise be difficult to obtain. You cleaned and processed the data, and you created a dataset of features that can be used for analysis. This is another important accomplishment, as it allows you to prepare the data for analysis and to identify the features that are most relevant to the task of sentiment analysis. You developed a machine learning model that can predict the sentiment of WhatsApp messages. This is a challenging task, but you have made significant progress in developing a model that is able to perform this task with some degree of accuracy.
Future work
Improve the accuracy of the machine learning model. This could be done by using a different algorithm, training the model on a larger dataset, or using a different feature set. Expand the dataset to include more WhatsApp chat logs. This would allow you to train the model on a more diverse set of data, which would improve the accuracy of the model. Develop a web application that can be used to analyze WhatsApp chat logs. This would allow users to easily analyze their own chat logs and to track the sentiment of their conversations over time. Use the model to predict the sentiment of other types of text data. For example, you could use the model to predict the sentiment of tweets, blog posts, or news articles. Use the model to improve customer service. For example, you could use the model to identify customers who are unhappy with a product or service, and then you could reach out to those customers to resolve the issue.
Log in or sign up for Devpost to join the conversation.