On real French news data, a preference-based greedy recommender matched neural Thompson sampling, and English translations performed nearly as well as original French embeddings.
What kind of news gatekeepers do we want machines to be? filter bubbles, fragmentation, and the normative dimensions of algorithmic recommendations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Preference-based learning for news headline recommendation
On real French news data, a preference-based greedy recommender matched neural Thompson sampling, and English translations performed nearly as well as original French embeddings.