I am now one step closer to finishing my doctorate. On Friday Oct 31, I defended my dissertation. The video of the presentation during the defense is provided below. I now only have to get a few documents signed and format my dissertation for publishing and I’ll be completely finished.
The title of my dissertation is: “Analysis of Twitter Messages for Sentiment and Insight for use in Stock Market Decision Making.”
The video is a bit over 1 hour and 12 minutes long. I cut out the question and answer session for the sake of brevity.
Using Twitter Sentiment in the Stock Market from Eric D Brown on Vimeo.
This video is a copy of my Doctoral Dissertation defense. The topic: Analysis of Twitter Messages for Sentiment and Insight for use in Stock Market Decision Making.
Dissertation Title: “Analysis of Twitter Messages for Sentiment and Insight for use in Stock Market Decision Making”
4 responses to “My Doctoral Dissertation Final Defense – Almost done”
This is great Eric! Thank you for sharing! I am about 32 minutes into your presentation. Will finish it tomorrow. In the meantime I had a couple of questions if you are open to helping me understand this better:
1 – How did the total marketcapitalization for XLE compare with XLP?
2- How were the 42 companies within each distributed between small caps/mid caps/large caps?
3- Is it possible, do you think, to extend the training data set to classify other kinds of sentiment (i.e. consumer interest in a product, for instance?) to see if there is a strength in leveraging the twitter data to do other types of sentiment classification?
Kind regards,
Susan
Hey Susan – thanks for the kind words and the question.
I don’t have the market cap data or distributions on hand but will go try to find it and throw it into a comment.
RE: extending the training data set for other types of classification – There is definitely other types of classifications that can be done with twitter sentiment. The training dataset can be built for any type of features to deliver all sorts of sentiment measures.
Thanks Eric! Appreciate it. Just finished listening to your complete presentation. Great explanations and appreciate your rigor. When you executed the Buy-and-Hold test, how consistently did you trade at a particular time of day or particular day of the week?
For the extreme tests, buys/sells were performed at the close of each trading day with the distribution of day of the week being fairly similar across all days.