I received an email asking how I would go about the detection of sarcasm in texts. I have a long standing interest in this topic, but only from the side lines, as I contribute to other NLP tasks (sentiment analysis, topic detection and recently, identification of emotions in text). A lot of papers on sarcasm have appeared but I didn’t review them. I’d be interested to see what approaches are explored to date. The following is how I would approach the task:

This post hopes to make a clear distinction between weak, strong and giant components, and I use the open-source code of Gephi to illustrate.

update: Best-Worst Scaling is now available on Nocode!

Gephi is a free software for network visualization, which is quite popular (more than 3 million downloads since it launched in 2010, and one million download in the last 2 years).

Umigon is the name of the function performing sentiment analysis, which I initially developed in 2012.

When creating a network from a text or a corpus of texts, the logic is to draw the terms that frequently appear (“co-occur”) together in the same sentences or paragraphs. The problem is, most frequent terms in these texts will be connected even if these connections don’t make a lot of sense.

What time have we got to develop an academic research project? What time have we got when we develop and launch an app, as an indie maker?

Many things to share about the new directions of research and development I am pursuing! Check the “about” page for a start!