Brian Roemmele Retweeted Brian Roemmele
My sentiment dictionary provides measures of valence and arousal for ~40,700 English words. Thus in-context the word health: v = (μ: 6.81, σ: 1.88), a = (μ: 5.13, σ: 2.35), fq = 105 Why is this important? Because you do not need to run rote machine learning AI to “know” this.https://twitter.com/BrianRoemmele/status/1100815485749256192 …
Brian Roemmele added,
Brian Roemmele @BrianRoemmele
I have mapped POMS and ANEW to 53 elements of speech both presented by the #VoiceFirst system and extracted by the user’s own speech. This is confirmed by up to 72 user telemetry points.
To my knowledge, and I studied this since the 1980s, no one has used AI in this manner. https://twitter.com/BrianRoemmele/status/1100811182544379905 …
0 replies
1 retweet
3 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.