A Review Selection Method based on Consumer Decision Phases in E-commerce

A valuable small subset strategically selected from massive online reviews is beneficial to improve consumers’ decision-making efficiency in e-commerce. Existing review selection methods primarily concentrate on the informativeness of and aim find a that can reflect informational properties original set. However, changes diets during two-phase decision process are not fully considered. In this study, we propose novel problem finding diet-matched with high diversity representativeness, which better adapt review-diet conversion attribute-oriented experience-oriented between two phases. decision-phase-based method named DPRS further proposed, involves steps: classification selection. step, probability being or estimated by prior knowledge-aware attentive neural network. second heuristic algorithm, namely stepwise non-dominated superiority strategy, introduced seek solution problem. Extensive experiments real-world dataset demonstrate outperforms state-of-the-art terms both