If you’ve ever wondered what the colour oftoday’s AI news is, wonder no more!
TLDR: NewsHues pulls the 20 most engaged AI stories from the bowels of the internet, performs sentiment analysis and then calculates and names a colour on a predefined spectrum. 8.3 out 10 users say its an easier way to understand what is happening in the world of ai that actually reading news!
The excellent NewsAPI is employed to fetch 20 of the day’s most engaged news articles based on our custom parameters and filters.
Sentiment analyses is handled by VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (Hutto, C.J. & Gilbert, E.E. (2014).(ICWSM-14). Ann Arbor, MI, June 2014).
VADER produces compound sentiment scores based on titles and article synopses, ranging from -1 (extremely negative) to +1 (extremely positive)
Sentiment scores are mapped to a predefined colour spectrum:
The final colour function converts each article’s hex colour to RGB values and calculates a weighted average of all article colours. Weights are based on the absolute value of sentiment scores. RGB components are averaged separately using these weights. this produces final RGB values, which are then converted back to a hex code.
Want an AI solution with a little more real-world utility?