This is the Trend Mining component for the main News Deframer project.
This component shows current talking points and visualizes rising trends over time. It also allows comparing coverage across different news sources and countries.
As a bonus, it helps to uncover "blind spots." Relying on a small set of news feeds can create gaps regarding important events. By showing what others are reading, this helps to discover relevant content outside of the usual bubble.
This approach may be based on the findings in this PhD Thesis.
We use a VAD/VAC (Dimensional) and BE5 (Discrete) approach to detect sentiments and emotions in texts, leveraging sentiment scores from MEmoLon, an emotion lexicon for 90+ languages. The VAD (Valence, Arousal, Dominance) model evaluates overall mood on a 1-9 scale across Valence (polarity/pleasantness), Arousal (activation/excitement), and Dominance (perceived control). The BE5 model measures the intensity of discrete emotions—Joy, Anger, Sadness, Fear, and Disgust—on a 1-5 scale.
There is fundamental science supporting this methodology: fMRT experiments demonstrate that reading specific words can indeed induce measurable emotional responses in the brain. For more details on this theory, refer to this PhD thesis.