Simbot, Give Me Five

Yian Shang, Elena Zheleva, Source, Apr 27, 2016
Commentary by Stephen Downes

This is the sort of thing I want to see enabled for a personal learning environment. It is, of course, a lot easier to do on a multti-user hosted platform such as Slack (using specialty applications called slackbots). Here's how it works: "The basis of our algorithm for finding similar articles is a neural network, which takes the words of each article and projects them into vectors of numbers. We then aggregate the word vectors for each of the words in an article to come up with an article vector. The vectors of numbers allow you to easily uncover the relationships between words and articles by applying different similarity measures, such as cosine similarity. Specifically, the neural network algorithm is word2vec, which was implemented through the Python topic-modeling library gensim." This is all off-the-shelf stuff for platforms these days. I can't wait to see it implemented in a personal graph.

Views: 0 today, 270 total (since January 1, 2017).[Direct Link]