The effect of user generated photos on review helpfulness prediction: An analytical approach
讲座名称：
The effect of user generated photos on review helpfulness prediction: An analytical approach
讲座时间：
2018-06-11
讲座人：
樊卫国
形式：
校区：
兴庆校区
实践学分：
讲座内容：
报告题目：The effect of user generated photos on review helpfulnessprediction: An analytical approach
报告人：樊卫国
报告时间：2018年6月11日（周一）下午3:00-4:30
报告地点：管理学院313
讲座摘要：Online reviews have been extensively studied in the hospitality andtourism literature. However, while user-provided photos embedded in onlinereviews accumulate in large quantities, their informational value has not beenwell understood likely due to technical challenges. The goal of this study isto introduce deep learning for computer vision to understand information valueof online hotel reviews. Using a dataset collected from two social media sites,we compared deep learning models with other machine learning techniques toexamine the effect of user-provided photos on review helpfulness. Findings showthat deep learning models were more useful in predicting review helpfulnessthan other models. While user-provided photos alone did not have the same impactas review texts, combining review texts and user-provided photos produced thehighest performance. Implications for the applications of deep learningtechnologies in hospitality and tourism research, as well as limitations anddirections for future research, are discussed.
相关视频