SERENE (uSer ExpeRiENce dEtector), also known as UX-SAD (User eXperience-Smells Automatic Detector), is a research project born in 2020, which comprises different components. As its name suggests, its primary goal is to provide a way to quickly and (semi-) automatically detect problems in the user experience of websites and web-based systems. Through a set of Artificial Intelligence (AI) models, SERENE detects users' emotions in web pages while guaranteeing users' privacy. Its main strength over typical user experience and usability evaluation is in the generalizability of its detections. While traditional methods use samples (that may not be representative), SERENE allows to tap into data provided by the whole user population. The platform is available at https://serene.ddns.net.
Augmenting Interviewer Judgments of Patient Experience with Automatic Language Analysis
INRIA(法国国家信息与自动化研究所);Carl von Ossietzky University of Oldenburg(奥尔登堡大学);German Research Center for Artificial Intelligence(德国人工智能研究中心);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
A Learning-Based Method for Automatic Operator Selection in the Fanoos XAI System
Carnegie Mellon University(卡内基梅隆大学)
我们描述了Fanoos XAI系统的扩展[Bayani et al 2022],它使系统能够学习采取适当的行动,以满足用户对或多或少抽象的描述的请求。具体来说,被分析系统的描述是以状态存储的,为了使描述或多或少地抽象,Fanoos从一个大型库中选择一个操作符应用于状态并生成新的描述。以前的工作主要使用手写的方法来选择操作员;目前的工作允许Fanoos利用经验来学习最佳操作员,以应用于特定情况,平衡探索和开发,利用专家的见解,并利用当前状态和过去状态之间的相似性。此外,为了引导学习过程(即,就像在课程学习中一样),我们描述了一个我们实现的模拟用户;这个模拟允许Fanoos获得一般的见解,从而实现合理的行动过程,这些见解以后可以通过与真实用户的经验进行改进,而不是完全从头开始与人类交互。实现本文中描述的方法的代码可以在https://github/DBay-ani/Operator_Selection_Learning_Extensions_For_Fanoos上找到。