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：tyc234cc 太阳成集团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.

报告人简介：樊卫国教授为美国爱荷华大学Tippie商学院Tippie商业分析主席，一直着力于数据挖掘，尤其是文本挖掘方向的科学研究。是国际上第一个利用遗传规划算法进行搜索引擎排序函数发现与优化的人，并在此专题上发表大量具有国际先进水平的文章。同时在基于互联网的网上搜索、自动问题回答、文本归纳，网上知识社区，电子商务竞争模式等方面都颇有建树。所发表的100多篇国际论文已有近2000次索引。现担任Management Science(MS)，Management Information System Quarterly (MISQ)，IEEE Transactions on Evolutionary Computation(TEC)，IEEETransactions on Knowledge and Data Engineering (TKDE)，ACM Transactions on Information Systems (TOIS)等期刊审稿人，以及IEEE Technical Committee on Digital Libraries成员，Journal of Database Management编委会成员，近20个国际会议评审委员。