Text entry in smartphones remains a critical element of mobile HCI. It has been widely studied in lab settings, using primarily transcription tasks, and to a far lesser extent through in-the-wild (field) experiments. So far it remains unknown how well user behaviour during lab transcription tasks approximates real use. In this paper, we present a study that provides evidence that lab text entry behaviour is clearly distinguishable from real world use. Using machine learning techniques, we show that it is possible to accurately identify the type of study in which text entry sessions took place. The implications of our findings relate to the design of future studies in text entry, aiming to support input with virtual smartphone keyboards.

中文翻译：

---

实验室和野外研究中的移动文本输入行为：有什么不同吗？

智能手机中的文本输入仍然是移动 HCI 的关键元素。它已在实验室环境中得到广泛研究，主要使用转录任务，并在较小程度上通过野外（现场）实验进行研究。到目前为止，实验室转录任务中的用户行为与实际使用的接近程度仍然未知。在本文中，我们提出了一项研究，该研究提供了证据，证明实验室文本输入行为与现实世界的使用明显不同。使用机器学习技术，我们表明可以准确识别文本输入会话发生的研究类型。我们的研究结果与未来文本输入研究的设计有关，旨在支持虚拟智能手机键盘的输入。