作成者 |
|
|
本文言語 |
|
出版者 |
|
発行日 |
|
収録物名 |
|
巻 |
|
号 |
|
開始ページ |
|
終了ページ |
|
会議情報 |
|
出版タイプ |
|
アクセス権 |
|
権利関係 |
|
|
関連DOI |
|
関連URI |
|
関連HDL |
|
概要 |
Product reviews can be helpful for consumers to nalize their purchasing decisions. The advertisement contains sentences intended by the seller. Meanwhile, the product review seems to be an honest impr...ession of the consumer, so it is easier to trust. However, in recent years, there are some problems such as fake reviews, guerilla marketing and increase in unhelpful reviews due to increase in users. Therefore, in many e-commerce sites, each reviews have “ Helpful ” and “ Not Helpful ”buttons for consumers to evaluate the helpfulness of the review. In this paper, we consider the ranking prediction model for helpfulness of Amazon reviews. First, we redefine the helpfulness score to take its reliability into consideration. In addition, we propose a loss function that can predict the helpfulness more accurately, and describe its theoretical explanation and the results of experiments.続きを見る
|