Skip to main content
QUICK REVIEW

[论文解读] The Impact of an AirBnb Host's Listing Description 'Sentiment' and Length On Occupancy Rates

Richard Diehl Martinez, Anthony Carrington|arXiv (Cornell University)|Nov 25, 2017
Aviation Industry Analysis and Trends被引用 5
一句话总结

本研究利用纽约市的数据,调查了 Airbnb 房东的房源描述情感倾向和长度是否会影响入住率。虽然较长的描述与更高的入住率相关,但通过 AFINN 词典衡量的正面情感并无显著影响;相反,评论数量和设施条件成为预订成功更强的预测指标。

ABSTRACT

There has been significant literature regarding the way product review sentiment affects brand loyalty. Intrigued by how natural language influences consumer choice, we were motivated to examine whether an AirBnb host's occupancy rate (how often their listing is booked out of the days they indicated their listing was available) can be determined by the perceived sentiment and length of their description summary. Our main goal, more generally, was to determine which features, including (but not limited to) sentiment and description length, most influence a host's occupancy rate. We define sentiment score through a natural language algorithm process, based on the AFINN dictionary. Using AirBnB data on New York City, our hypothesis is that higher sentiment scores (more positive descriptions) and longer summary length lead to higher occupancy rates. Our results show that while longer summary length may positively influence occupancy rates, more positive summary descriptions have no effect. Instead, we find that other factors such as number of reviews and number of amenities, in addition to summary length, are better indicators of occupancy rate.

研究动机与目标

  • 确定 Airbnb 房源描述的情感倾向和长度是否会影响其入住率。
  • 探讨房东描述中的自然语言特征如何影响消费者的预订行为。
  • 识别除情感和长度外,对入住率预测最强的房源属性。
  • 评估语言特征与有形设施及社交证明(如评论)对预订结果的相对影响。

提出的方法

  • 应用 AFINN 情感词典,为每条房源描述计算情感得分。
  • 通过词数测量描述长度,以评估其对入住率的影响。
  • 使用多元回归分析,将入住率建模为情感、长度、评论数量、设施及其他房源特征的函数。
  • 聚焦于公开数据中的纽约市 Airbnb 房源。
  • 控制房东特异性和房源特异性协变量,以隔离文本特征的影响。
  • 采用统计建模方法,在调整混杂变量后检验情感和长度的显著性。

实验结果

研究问题

  • RQ1房源描述中更积极的情感倾向是否会导致更高的入住率?
  • RQ2更长的房源描述是否能提高被预订的可能性?
  • RQ3在控制其他房源特征后,情感和描述长度是否仍是入住率的显著预测因子?
  • RQ4在语言特征与有形因素中,哪类因素对入住率的预测力最强?

主要发现

  • 较长的房源描述与更高的入住率正相关,表明更详细的描述可提升预订表现。
  • 与预期相反,通过 AFINN 词典得出的更高情感得分与入住率之间无统计显著关系。
  • 房源的评论数量比情感或描述长度更能预测入住率。
  • 房源中设施的存在与否及其数量对入住率的影响,大于语言特征。
  • 在控制其他变量后,情感得分无法显著提升入住率预测模型的表现。
  • 即使在模型中包含评论数量和设施等其他特征后,描述长度仍是显著预测因子。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。