SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement.
Proceedings of The Web Conference 2020 , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A deep Q-learning algorithm solves the fairness-aware profit maximization problem on social networks and reports up to 10 times higher profit than baselines on real datasets while meeting community fairness thresholds.
citing papers explorer
-
From Documents to Segments: A Contextual Reformulation for Topic Assignment
SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement.
-
Fairness-Aware Profit Maximization using Deep Reinforcement Learning
A deep Q-learning algorithm solves the fairness-aware profit maximization problem on social networks and reports up to 10 times higher profit than baselines on real datasets while meeting community fairness thresholds.