“Sport – Football/Soccer Players Summer Transfers Season 2022-23” was succeeded by 56 entries, 200+ analysis Pages, 650+DAX measures, and 500+ Navigation buttons, bookmarks, and tooltips. Thanks for everyone’s engagement and dedication.
The goal of this build is to analyze a dataset of tweets that mention a particular stock or stocks and to identify interesting insights based on the text of the tweets and the stock references or tags within the tweets. You will extract features such as the volume of tweets, sentiment of tweets, length of tweets, and time of tweets, and use these features to explore the data and look for trends and patterns. You will then visualize your findings and present your insights in a report or presentation.
Collect a dataset of tweets that mention a particular stock or stocks.
Pre-process the tweet data. This might involve cleaning up the text (e.g. removing hashtags, URLs, etc.), tokenizing the text, and possibly removing stop words.
Extract features from the tweet data. Some possible features to consider include:
The volume of tweets: You could count the number of tweets that mention a particular stock.
The sentiment of tweets: You could use a pre-trained sentiment analysis model to classify the sentiment of each tweet as positive, negative, or neutral.
The length of tweets: You could measure the length of each tweet in terms of the number of words or characters.
The time of tweets: You could extract the timestamp of each tweet and use it to analyze trends over time.
Explore the data and look for interesting insights. For example, you might find that the volume of tweets about a particular stock is correlated with its price, or that the sentiment of tweets tends to be more negative when the stock price is falling.
Visualize your findings. Use charts, graphs, and other visualizations to communicate your insights to others.
A report or presentation summarizing the findings and conclusions of the analysis. This could include visualizations of the data, such as charts and graphs, as well as written explanations of the insights that were discovered.
A codebase containing the scripts and functions that were used to collect and analyze the tweet data. This could include code for pre-processing the text, extracting features, and visualizing the results.
A dataset of tweets that were collected and analyzed as part of the project. This could be a CSV file or other format that contains the raw data, as well as any additional features that were extracted from the tweets.
A set of instructions or documentation explaining how the project was completed, including any challenges that were encountered and how they were overcome.
We always encourage all participants to provide a summary with the most insightful, instructional explanation of how they constructed their reports and met their personal learning objectives for the challenge.
If you need any help with publishing, please reach out to one of the team managers for assistance (post in the forum/LinkedIn group) or email firstname.lastname@example.org
This is an entry submitted by Justin Bong via On Demand.
Here’s how Justin described it:
The Tweets Dashboard displays the tweets spread for each stocks across different quarters for the year 2022. It also showcase the tweets heatmap on popularity of stocks tweeted and the most tweeted word within that year. The tweets can be searched and filtered for further review and automatically calculated in the tweets count.
My Twitter Thread Analysis shows KPI such as: percent share of @ account, avg tweet lenght, the number of days since the tweet was published, # number and @account number.
You can also check the number of tweets per day, month, quarter and year. My report displays top 5 @ accounts and companies as well.
Hi, I am Sonam Mehra and here is my late submission for Twitter Thread Analysis (thought 9th is the last date). The analysis was conducted on the AAPL stock price from January 2022 to December 2022 along with the analysis of tweets during the same period. The sentiment analysis revealed a weak correlation between the closing stock price and tweets. The dashboard was designed with a Twitter-like feel by adding trending topics in Canada. Data cleaning and manipulation were performed using pandas, while snscrape package and Twitter API were used for scraping tweets about the stock and trends, respectively.
It’s truly remarkable to witness the growth and success of ““Twitter Threads Analysis.”” The 56 entries, 200+ analysis pages, 650+ DAX measures, and 500+ navigation buttons, bookmarks, and tooltips are a testament to the hard work and dedication put into this project. Your engagement with the community has clearly paid off, and it’s evident that you’re providing valuable content.If you ever find the need to expand your social media presence or explore new avenues, you might consider options like 100 free TikTok likes. This can be a valuable strategy to enhance your visibility on platforms like TikTok.