Using Variable Dwell Time to Accelerate Gaze-Based Web Browsing with Two-Step Selection

📝 Abstract

In order to avoid the “Midas Touch” problem, gaze-based interfaces for selection often introduce a dwell time: a fixed amount of time the user must fixate upon an object before it is selected. Past interfaces have used a uniform dwell time across all objects. Here, we propose a gaze-based browser using a two-step selection policy with variable dwell time. In the first step, a command, e.g. “back” or “select”, is chosen from a menu using a dwell time that is constant across the different commands. In the second step, if the “select” command is chosen, the user selects a hyperlink using a dwell time that varies between different hyperlinks. We assign shorter dwell times to more likely hyperlinks and longer dwell times to less likely hyperlinks. In order to infer the likelihood each hyperlink will be selected, we have developed a probabilistic model of natural gaze behavior while surfing the web. We have evaluated a number of heuristic and probabilistic methods for varying the dwell times using both simulation and experiment. Our results demonstrate that varying dwell time improves the user experience in comparison with fixed dwell time, resulting in fewer errors and increased speed. While all of the methods for varying dwell time resulted in improved performance, the probabilistic models yielded much greater gains than the simple heuristics. The best performing model reduces error rate by 50% compared to 100ms uniform dwell time while maintaining a similar response time. It reduces response time by 60% compared to 300ms uniform dwell time while maintaining a similar error rate.

💡 Analysis

In order to avoid the “Midas Touch” problem, gaze-based interfaces for selection often introduce a dwell time: a fixed amount of time the user must fixate upon an object before it is selected. Past interfaces have used a uniform dwell time across all objects. Here, we propose a gaze-based browser using a two-step selection policy with variable dwell time. In the first step, a command, e.g. “back” or “select”, is chosen from a menu using a dwell time that is constant across the different commands. In the second step, if the “select” command is chosen, the user selects a hyperlink using a dwell time that varies between different hyperlinks. We assign shorter dwell times to more likely hyperlinks and longer dwell times to less likely hyperlinks. In order to infer the likelihood each hyperlink will be selected, we have developed a probabilistic model of natural gaze behavior while surfing the web. We have evaluated a number of heuristic and probabilistic methods for varying the dwell times using both simulation and experiment. Our results demonstrate that varying dwell time improves the user experience in comparison with fixed dwell time, resulting in fewer errors and increased speed. While all of the methods for varying dwell time resulted in improved performance, the probabilistic models yielded much greater gains than the simple heuristics. The best performing model reduces error rate by 50% compared to 100ms uniform dwell time while maintaining a similar response time. It reduces response time by 60% compared to 300ms uniform dwell time while maintaining a similar error rate.

📄 Content

Running head: VARIABLE DWELL TIME FOR GAZE-BASED BROWSING
1

This is an Accepted Manuscript of an article published by Taylor & Francis in the International Journal of Human-Computer Interaction on 30 March, 2018, available online: http://www.tandfonline.com/10.1080/10447318.2018.1452351 . For an eprint of the final published article, please access: https://www.tandfonline.com/eprint/T9d4cNwwRUqXPPiZYm8Z/full (limited number).

VARIABLE DWELL TIME FOR GAZE-BASED BROWSING
2 Using Variable Dwell Time to Accelerate Gaze-based Web Browsing with Two-step Selection Zhaokang Chen and Bertram E. Shi The Hong Kong University of Science and Technology, Hong Kong Author Note This work was supported in part by the Hong Kong Research Grants Council General Research Fund grant #16209014.
Zhaokang Chen, Department of Electronic and Computer Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
Bertram E. Shi, Department of Electronic and Computer Engineering and Department of Chemical and Biological Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong. Correspondence concerning this article should be addressed to Bertram E. Shi, Department of Electronic and Computer Engineering and Department of Chemical and Biological Engineering, the Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong. E-mail: eebert@ust.hk VARIABLE DWELL TIME FOR GAZE-BASED BROWSING
3 ABSTRACT In order to avoid the “Midas Touch” problem, gaze-based interfaces for selection often introduce a dwell time: a fixed amount of time the user must fixate upon an object before it is selected. Past interfaces have used a uniform dwell time across all objects. Here, we propose a gaze-based browser using a two-step selection policy with variable dwell time. In the first step, a command, e.g. “back” or “select”, is chosen from a menu using a dwell time that is constant across the different commands. In the second step, if the “select” command is chosen, the user selects a hyperlink using a dwell time that varies between different hyperlinks. We assign shorter dwell times to more likely hyperlinks and longer dwell times to less likely hyperlinks. In order to infer the likelihood each hyperlink will be selected, we have developed a probabilistic model of natural gaze behavior while surfing the web. We have evaluated a number of heuristic and probabilistic methods for varying the dwell times using both simulation and experiment. Our results demonstrate that varying dwell time improves the user experience in comparison with fixed dwell time, resulting in fewer errors and increased speed. While all of the methods for varying dwell time resulted in improved performance, the probabilistic models yielded much greater gains than the simple heuristics. The best performing model reduces error rate by 50% compared to 100ms uniform dwell time while maintaining a similar response time. It reduces response time by 60% compared to 300ms uniform dwell time while maintaining a similar error rate.
Keywords: Human computer interface, Gaze tracking, Hidden Markov models, Inference algorithms, Browsers, Bayes methods VARIABLE DWELL TIME FOR GAZE-BASED BROWSING
4 INTRODUCTION The use and capabilities of eye trackers have expanded rapidly in recent years. A state-of- the-art eye tracker can estimate eye gaze on a monitor screen accurately enough to allow users to interact with a computer system. This is especially useful for people with motor disabilities (Poole & Ball, 2006). Eye movement can be regarded as a very fast interaction modality and can be very informative about users’ intent. As a result, use of eye movements is getting more and more attention in the field of human computer interaction (HCI) (Majaranta & Bulling, 2014). Many innovative human computer interfaces have been designed using eye tracking devices. One of the most common uses of eye gaze is for object selection (Majaranta, Ahola, & Špakov, 2009; Zander, Gaertner, Kothe, & Vilimek, 2010). Enabling a user to select an object by looking at it might seem quite simple and intuitive. However, one of the most challenging problems for gaze interfaces is the “Midas Touch” problem: it is difficult to distinguish between the spontaneous eye movements used to gather visual information and the intentional eye movements for explicit selection (Jacob, 1995). The most common way to avoid unintentional selection is to introduce a dwell time: users must maintain their eye gaze on an object for a predefined duration before it is selected (Majaranta et al., 2009; Murata, 2006; Räihä & Ovaska, 2012).
Some user interfaces avoid this problem by using gaze only to augment other input modalities. These “attentive user interfaces” (Majaranta & Bulling, 2014) only monitor the users’ natural eye movements subtly in the background

This content is AI-processed based on ArXiv data.