Week 12 – Pre Mortem

--Originally published at TC3045 – Sagnelli's blog

Coming back from holy week holidays, and I really need a second week off. However, it is time to return to our duties, and continue with this development. We are only a month away from finishing this course.

Last thing we were focusing on was the front end part of the app. This is the second phase of the project so to speak. We will be focusing on applying the sentiment analysis to show charts on the frontend, also to apply the backend to build the graphic word cloud, and give proper information, and direction on which candidate is leading the poll.

Stay tuned!

Week 11 – Pre Mortem

--Originally published at TC3045 – Sagnelli's blog


This is the week where the sprint presentation is going to be upheld. On Tuesday will demonstrate our advancements on the functionality of our project so far. Next steps of the project are to be determined, but are mostly related to front-end integration with what we already have.

Stay tuned for the results of this week.

Week 10 Post-Mortem

--Originally published at TC3045 – Sagnelli's blog


This week I saw some great advancements on our project. Alfonso, and I finished styling the code for the words counting functionality of the word cloud. The graphic stuff is going to be developed in the front-end; however, the basic functionality of distinguishing which words are most frequently used by candidates is already done. We used a library from Python named Counter to do this. The current output of our word cloud program is a list of words with their respective number of appearances.

This is what we are going to present on the sprint presentation on Tuesday because on Friday the classrooms where occupied, so the presentation was moved.

Be sure to hear of what the next steps are going to be.

Week 6: Post mortem

--Originally published at TC3045 – Sagnelli's blog

This week we were able to read emojis in tweets, and separate user name from the tweet itself. By doing this, we avoid analyzing user names, and actually analyze the tweet itself. By reading emojis we can have a more accurate idea on what the person’s intention is. We can implement analysis in the text comparison to the emoji meaning. Henceforth, this week we could say that the preparations for the mining phase is over. We are now able to mine data of certain important people, of certain words, and to gather the complete data of these tweets.

For the upcoming partial, we are going to start mining data, and doing preparations for the analysis of this data. Moreover, we are going to eliminate stop words, and focus on what the tweet is actually trying to communicate. Henceforth, we are going to show a map of which words are most used, and who is actually winning this electoral campaign.