A note to mobile/tablet readers that this blog is best viewed in landscape mode
This project is based on a personal passion of mine in the mental health space based on my deep interest in natural language processing.
In this post, I will share my insights based on the first iteration of this agile project.
What are my goals?
What are my success factors?The metrics or key success factors have been split separately for scraping, topic modelling and sentiment analysis:
InsightsBased on the word phrases from the topic models and visual examination of the posts:
What risks/limitations/assumptions affect these findings?
Graphical findings and interesting code snippets from the first iteration: Following visual examination, I wanted to see the overall sentiment score of the forum thread: Read more if you are tech-savvy to unravel the surprise technical summary below:Model Selection and Implementation
Implementation and EvaluationScraping
InferenceFrom the topic models, we are able to make inferences about the commonly used phrases in the forum thread. Also, using sentiment analysis, we inferred that the overall sentiment of the forum thread was mainly neutral and positive. There was hardly any negativity in the forum thread which is expected in a forum of this kind. Positive reinforcement, active listening and constructive suggestions were present in this forum.Comments are closed.
|
From The EditorWelcome to my Vizard of Oz blog. The name Vizard is a play on the word viz (short for visualisation) and wizard. As an Australian blogger who loves data visualisation, this blog has been fittingly named Vizard of Oz. Topics that I will talk about include all things data but will focus particularly on data visualisation, data engineering and predictive analytics. ArchivesCategories
All
This website uses marketing and tracking technologies. Opting out of this will opt you out of all cookies, except for those needed to run the website. Note that some products may not work as well without tracking cookies. Opt Out of Cookies |