Segment topicality: how well each part of a video fits the query
RESONEO says this twiddler measures topicality, the fit to the query, for each segment of a video. Only a settings object is known, and Google has not described the twiddler.
01What is known
The schema object is VideoSegmentTopicalityTwiddlerParams in the quality_video namespace. Params are settings sent with the query. RESONEO adds that topicality is measured per segment of the video. Topicality is the search term for how well a result matches the topic of a query.
Together with the video passages twiddler this points to a video being judged in parts, not only as a whole. Like every twiddler it only recommends; the twiddler framework in Superroot, the layer that merges what Google's indexes return, makes the decision.
02Context and limits
Google Search documents that it detects segments in videos automatically and shows them as key moments. Per-segment topicality would be a natural ingredient for choosing which segment to show, but no Google text says so. How segments are cut, which signals define their topic and how much the twiddler moves a result are unknown.
Topicality is relevance, not quality. The parent article places the image and video twiddlers outside this site's E-E-A-T system map. On our map it belongs to the twiddler layer, nothing more.