Results 1 - 10
of
85
Predicting Human Interruptibility with Sensors: A Wizard of Oz Feasibility Study
- CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS
, 2003
"... A person seeking someone else's attention is normally able to quickly assess how interruptible they are. This assessment allows for behavior we perceive as natural, socially appropriate, or simply polite. On the other hand, today's computer systems are almost entirely oblivious to the huma ..."
Abstract
-
Cited by 284 (27 self)
- Add to MetaCart
A person seeking someone else's attention is normally able to quickly assess how interruptible they are. This assessment allows for behavior we perceive as natural, socially appropriate, or simply polite. On the other hand, today's computer systems are almost entirely oblivious to the human world they operate in, and typically have no way to take into account the interruptibility of the user. This paper presents a Wizard of Oz study exploring whether, and how, robust sensor-based predictions of interruptibility might be constructed, which sensors might be most useful to such predictions, and how simple such sensors might be. The study simulates a range of possible sensors through human coding of audio and video recordings. Experience sampling is used to simultaneously collect randomly distributed self-reports of interruptibility. Based on these simulated sensors, we construct statistical models predicting human interruptibility and compare their predictions with the collected self-report data. The results of these models, although covering a demographically limited sample, are very promising, with the overall accuracy of several models reaching about 78%. Additionally, a model tuned to avoiding unwanted interruptions does so for 90% of its predictions, while retaining 75% overall accuracy.
Examining the Robustness of Sensor-Based Statistical Models of Human Interruptibility
- Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2004
, 2004
"... Current systems often create socially awkward interruptions or unduly demand attention because they have no way of knowing if a person is busy and should not be interrupted. Previous work has examined the feasibility of using sensors and statistical models to estimate human interruptibility in an of ..."
Abstract
-
Cited by 105 (15 self)
- Add to MetaCart
Current systems often create socially awkward interruptions or unduly demand attention because they have no way of knowing if a person is busy and should not be interrupted. Previous work has examined the feasibility of using sensors and statistical models to estimate human interruptibility in an office environment, but left open some questions about the robustness of such an approach. This paper examines several dimensions of robustness in sensor-based statistical models of human interruptibility. We show that real sensors can be constructed with sufficient accuracy to drive the predictive models. We also create statistical models for a much broader group of people than was studied in prior work. Finally, we examine the effects of training data quantity on the accuracy of these models and consider tradeoffs associated with different combinations of sensors. As a whole, our analyses demonstrate that sensor-based statistical models of human interruptibility can provide robust estimates for a variety of office workers in a range of circumstances, and can do so with accuracy as good as or better than people. Integrating these models into systems could support a variety of advances in human computer interaction and computer-mediated communication. Author Keywords Situationally appropriate interaction, managing human attention, sensor-based interfaces, context-aware computing, machine learning.
Effects of Intelligent Notification Management on Users and Their Tasks
- Proceedings of the ACM Conference on Human Factors in Computing Systems
, 2008
"... We present a novel system for notification management and report results from two studies testing its performance and impact. The system uses statistical models to realize defer-to-breakpoint policies for managing notifications. The first study tested how well the models detect three types of breakp ..."
Abstract
-
Cited by 40 (3 self)
- Add to MetaCart
(Show Context)
We present a novel system for notification management and report results from two studies testing its performance and impact. The system uses statistical models to realize defer-to-breakpoint policies for managing notifications. The first study tested how well the models detect three types of breakpoints within novel task sequences. Results show that the models detect breakpoints reasonably well, but struggle to differentiate their type. Our second study explored effects of managing notifications with our system on users and their tasks. Results showed that scheduling notifications at breakpoints reduces frustration and reaction time relative to delivering them immediately. We also found that the relevance of notification content determines the type of breakpoint at which it should be delivered. The core concept of scheduling notifications at breakpoints fits well with how users prefer notifications to be managed. This indicates that users would likely adopt the use of notification management systems in practice.
Toolkit Support for Developing and Deploying Sensor-Based Statistical Models of Human Situations
- To Appear, CHI
, 2007
"... Sensor-based statistical models promise to support a variety of advances in human-computer interaction, but building applications that use them is currently difficult and potential advances go unexplored. We present Subtle, a toolkit that removes some of the obstacles to developing and deploying app ..."
Abstract
-
Cited by 29 (3 self)
- Add to MetaCart
(Show Context)
Sensor-based statistical models promise to support a variety of advances in human-computer interaction, but building applications that use them is currently difficult and potential advances go unexplored. We present Subtle, a toolkit that removes some of the obstacles to developing and deploying applications using sensor-based statistical models of human situations. Subtle provides an appropriate and extensible sensing library, continuous learning of personalized models, fully-automated high-level feature generation, and support for using learned models in deployed applications. By removing obstacles to developing and deploying sensor-based statistical models, Subtle makes it easier to explore the design space surrounding sensor-based statistical models of human situations. Subtle thus helps to move the focus of human-computer interaction research onto applications and datasets, instead of the difficulties of developing and deploying sensor-based statistical models. Author Keywords Toolkits, Subtle, sensor-based statistical models, machine
K.: Improving cell phone awareness by using calendar information
- In Proceedings of INTERACT
, 2005
"... Abstract. The many benefits that cell phones provide are at times overshadowed by the problems they create, as when one person’s cell phone disrupts a group activity, such as a class, meeting or movie. Cell phone interruption is only highlighted by the ever increasing number of mobile devices we car ..."
Abstract
-
Cited by 19 (5 self)
- Add to MetaCart
(Show Context)
Abstract. The many benefits that cell phones provide are at times overshadowed by the problems they create, as when one person’s cell phone disrupts a group activity, such as a class, meeting or movie. Cell phone interruption is only highlighted by the ever increasing number of mobile devices we carry. Many tools and techniques have been proposed in order to minimize interruption caused by mobile devices. In the current study, we use calendar information to infer users ’ activity and to automatically configure cell phones accordingly. Our in-situ experiment uses PDAs that run a cell phone simulator to examine the feasibility and design factors of such a solution. Our results show that both structured activities and appropriate cell phone configuration can be predicted with high accuracy using the calendar information. The results also show consistent mapping of activities to configuration for each individual. However there was a poor consistency of mapping activity to configuration across different participants. We discuss the results in relation to inaccuracy, spontaneous activities, and user reactions. 1
Using Relationship to Control Disclosure in Awareness Servers
- In Proceedings of Graphics Interface 2005 (GI
, 2005
"... Awareness servers provide information about a person to help observers determine whether a person is avail-able for contact. A tradeoff exists in these systems: more sources of information, and higher fidelity in those sources, can improve people’s decisions, but each increase in information reduces ..."
Abstract
-
Cited by 19 (3 self)
- Add to MetaCart
(Show Context)
Awareness servers provide information about a person to help observers determine whether a person is avail-able for contact. A tradeoff exists in these systems: more sources of information, and higher fidelity in those sources, can improve people’s decisions, but each increase in information reduces privacy. In this paper, we look at whether the type of relationship between the observer and the person being observed can be used to manage this tradeoff. We conducted a survey that asked people what amount of information from different sources that they would disclose to seven different rela-tionship types. We found that in more than half of the cases, people would give different amounts of informa-tion to different relationships. We also found that the only relationship to consistently receive less informa-tion was the acquaintance – essentially the person with-out a strong relationship at all. Our results suggest that awareness servers can be improved by allowing finer-grained control than what is currently available.
Should I Call Now? Understanding What Context is Considered When Deciding Whether to Initiate Remote Communication via Mobile Devices
"... Requests for communication via mobile devices can be disruptive to the current task or social situation. To reduce the frequency of disruptive requests, one promising approach is to provide callers with cues of a receiver’s context through an awareness display, allowing informed decisions of when to ..."
Abstract
-
Cited by 15 (0 self)
- Add to MetaCart
(Show Context)
Requests for communication via mobile devices can be disruptive to the current task or social situation. To reduce the frequency of disruptive requests, one promising approach is to provide callers with cues of a receiver’s context through an awareness display, allowing informed decisions of when to call. Existing displays typically provide cues based on what can be readily sensed, which may not match what is needed during the call decision process. In this paper, we report results of a four week diary study of mobile phone usage, where users recorded what context information they considered when making a call, and what information they wished others had considered when receiving a call. Our results were distilled into lessons that can be used to improve the design of awareness displays for mobile devices, e.g., show frequency of a receiver’s recent communication and distance from a receiver to her phone. We discuss technologies that can enable cues indicated in these lessons to be realized within awareness displays, as well as discuss limitations of such displays and issues of privacy.
Privacy in the open: how attention mediates awareness and privacy in open-plan offices
- In ACM GROUP
, 2007
"... The tension between privacy and awareness has been a persistent difficulty in distributed environments that support opportunistic and informal interaction. For example, many awareness systems that display ‘always-on ’ video links or PC screen contents have been perceived as too invasive, even though ..."
Abstract
-
Cited by 14 (6 self)
- Add to MetaCart
(Show Context)
The tension between privacy and awareness has been a persistent difficulty in distributed environments that support opportunistic and informal interaction. For example, many awareness systems that display ‘always-on ’ video links or PC screen contents have been perceived as too invasive, even though functional real-world analogues, like open-plan offices, may provide even less privacy than their online counterparts. In this paper we explore the notion of privacy in open-plan real-world environments, in order to learn more about how it might be supported in distributed systems. From interviews and observations in four open-plan offices, we found that attention plays an important role in the management of both confidentiality and solitude. The public nature of paying attention allows people to build understandings of what objects in a space are legitimate targets for attention and allows people to advertise their interest in interaction. Our results add to what is known about how privacy works in real-world spaces, and suggest valuable design ideas that can help improve support for natural privacy control and interaction in distributed awareness systems.
Oasis: A Framework for Linking Notification Delivery to the Perceptual Structure of Goal-Directed Tasks
"... A notification represents the proactive delivery of information to a user and reduces the need to visually scan or repeatedly check an external information source. At the same time, notifications often interrupt user tasks at inopportune moments, decreasing productivity and increasing frustration. C ..."
Abstract
-
Cited by 13 (1 self)
- Add to MetaCart
A notification represents the proactive delivery of information to a user and reduces the need to visually scan or repeatedly check an external information source. At the same time, notifications often interrupt user tasks at inopportune moments, decreasing productivity and increasing frustration. Controlled studies have shown that linking notification delivery to the perceptual structure of a user’s tasks can reduce these interruption costs. However, in these studies, the scheduling was always performed manually, and it was not clear whether it would be possible for a system to mimic similar techniques. This article contributes the design and implementation of a novel system called Oasis that aligns notification scheduling with the perceptual structure of user tasks. We describe the architecture of the system, how it detects task structure on the fly without explicit knowledge of the task itself, and how it layers flexible notification scheduling policies on top of this detection mechanism. The system also includes an offline tool for creating customized statistical models for detecting task structure. The value of our system is that it intelligently schedules notifications, enabling the reductions in interruption costs shown within prior controlled studies to now be realized by users in everyday desktop computing tasks. It also provides a test bed for experimenting with how notification management policies and other system functionalities can be linked to task
