Dec 2022-

Twitter-Project

"What we can Learn From Tweets?"

By delving into the realm of tweet analysis, we unlock a treasure trove of valuable insights that weave together the fabric of human interactions and sentiments. Within the vast expanse of tweets, we uncover a rich tapestry of trends, uncovering the pulse of popular discourse, emerging topics, and shifting narratives. Through meticulous examination of linguistic nuances, contextual cues, and sentiment analysis, we decipher the emotional undercurrents, capturing the ebb and flow of public opinion. From the highs of collective joy to the lows of shared concerns, tweets provide a unique window into the collective consciousness, enabling us to comprehend societal shifts, anticipate emerging patterns, and forge informed strategies.


In December 2022, Me and my teammate Fereshte Mohammadi initiated Twitter Project with the aim of fetching tweets from Twitter to furnish users with insightful analytical information regarding those tweets. In the initial stage of the project, our focus lies on presenting users with three informative bar charts: the most frequently used words, popular hashtags, and prominent mentions, all associated with a specific hashtag. These visualizations offer a concise and engaging overview of the key elements within the tweet data, providing users with a comprehensive snapshot of the prevailing trends and patterns.


Project Start page:

The Following picture shows the GUI of our project where the Users can put specific hashtag and their desired date and number of tweets to search for.

First Stage

After retrieving tweets from twitter we store those tweets in a separate file in the users directory :

Second Stage

In the Next stage, three bar chart( The most frequent word, Hashtag and mention) is showned to the user. which contains a specific hashtag.

Last Stage

In the Last step, we focus on cleaning the text of the tweets to ensure they are in a suitable format for further analysis using natural language processing (NLP) models. This data cleaning step helps to remove any noise or irrelevant information, allowing us to derive more accurate insights from the text. The cleaned tweets is also stored in the user's directory.

In Near Future:

In the End I should mention this is the first version of this project and we are looking forward to expand this project by adding more statistical and insight about the tweets with specific hashtag and also build NLP model for sentimental analysis on those tweets.

Project Demo :

In the Following video you can see the full view of the project

Skills I developed in this project:

Python Programming: I have strengthened my proficiency in Python, using it as the primary programming language for data retrieval, data cleaning, analysis, and visualization tasks.I have become adept at leveraging Python libraries and packages to efficiently process and manipulate tweet data.

Data Retrieval: I have gained proficiency in fetching and retrieving data from external sources, specifically Twitter, using APIs such as Tweepy and snscrape.

Data Cleaning and Preparation: I have developed expertise in cleaning and preprocessing tweet text data, ensuring its readiness for subsequent analysis. This includes techniques such as removing unnecessary characters, handling missing data, and standardizing the text format.

Data Visualization: I have enhanced my skills in creating visually compelling and informative visualizations using Python libraries like Matplotlib and Seaborn.

Graphical User Interface (GUI) Development: I have gained proficiency in building user-friendly interfaces using libraries such as Streamlit. This has allowed me to create intuitive and interactive dashboards that enable users to explore and interact with the tweet analysis results effortlessly.

Project Management and Using GitHub: Throughout the project, I have developed essential project management skills, including task prioritization, time management, and collaboration with team members through GitHub.