Sentiment analysis in Protobi
February 14, 2019
Valentines Day can send a lot of confusing messages. You can evaluate them in Protobi using sentiment analysis.
These libraries score text on a scale from 0 to 100%, where 100% is very positive, 0% is very negative, and 50% is neutral. Here’s one example scoring a random list of adjectives:
At heart, computerized sentiment analysis is a bit simplistic from a human perspective. It scores the words within the text and returns an aggregrate summary score. The computer doesn’t really get in the mind of the author to divine the actual sentiment.
The scores in the image above are literally taken from the algorithm. We assume it’s rating “XOXO” as only 0.67 because it doesn’t really grok the meaning.
For instance it rates the following as having a high sentiment even though that’s totally not what this sentence is saying:
“You’re really nice, but…” (80%)
And it rates the following as having a low sentiment even though might intend to communicate quite the opposite:
“You’re not half bad” (32%)
And it may completely miss subtle British-vs-American inflections, at least according to this Guardian reporter on English-to-English: “quite” explained
“Quite good” (98%)
Automated sentiment analysis can be very effective at sorting through lots of verbal expressions and extracting general trends
Available for beta testing
Sentiment analysis is currently in beta and can be enabled for your project. Contact email@example.com