清晰
旅游
计算机科学
社会化媒体
钥匙(锁)
情绪分析
SPARK(编程语言)
心理学
认知心理学
业务
人工智能
政治学
万维网
化学
程序设计语言
法学
生物化学
计算机安全
作者
Yihong Chen,Tao Hu,Rob Law
标识
DOI:10.1080/13683500.2024.2378608
摘要
Discover the secrets to crowdfunding triumph. In start-up tourism enterprises, mastering the art of captivating and converting users into sponsors through multimodal stimuli is paramount. Researchers used deep learning to deeply mine the text, images and video promotional content of 3,659 travel crowdfunding projects and nine classifiers to predict crowdfunding project success dynamically. We unearthed fascinating insights: Images spark attention, but video and text drive user conversion to sponsorship. Speech tends to deliver information, facts, or opinions. Key successful project predictors include positive emotions, pro-social engagement, cognitive vocabulary, increased video scenes and rapid visual variation. While consistent multimodal data bolsters model clarity, it does not markedly boost prediction. Lastly, linear and tree-based models outperform their nonlinear counterparts and have better prediction results.
科研通智能强力驱动
Strongly Powered by AbleSci AI