topauthor: Kristensson_P* : Human-Computer Interaction Bibliography Search

= ^ + EN RW G Using ensembles of decision trees to automate repetitive tasks in web applications Supporting context and inference / Bray, Zachary / Kristensson, Per Ola ACM SIGCHI 2010 Symposium on Engineering Interactive Computing Systems 2010 p.35-40

Keywords: end-user programming, programming by example

doi.acm.org/10.1145/1822018.1822025 ACM Digital Library

Summary: Web applications such as web-based email, spreadsheets and form filling applications have become ubiquitous. However, many of the tasks that users try to accomplish with such web applications are highly repetitive. In this paper we present the design of a system we have developed that learns and thereafter automates users' repetitive tasks in web applications. Our system infers users' intentions using an ensemble of decision trees. This enables it to handle branching, generalization and recurrent changes of relative and absolute positions. Our evaluation shows that our system converges to the correct solution after 3-8 iterations when the pattern is noise-free, and after 3-14 iterations for a noise level between 5-35%.

= ^ + EN RW G Text entry performance of state of the art unconstrained handwriting recognition: a longitudinal user study Non-traditional interaction techniques / Kristensson, Per Ola / Denby, Leif C. Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009 v.1 p.567-570

Keywords: handwriting, handwriting recognition, software keyboard

doi.acm.org/10.1145/1518701.1518788 ACM Digital Library

Summary: We report on a longitudinal study of unconstrained handwriting recognition performance. After 250 minutes of practice, participants had a mean text entry rate of 24.1 wpm. For the first four hours of usage, entry and error rates of handwriting recognition are about the same as for a baseline QWERTY software keyboard. Our results reveal that unconstrained handwriting is faster than what was previously assumed in the text entry literature.

= ^ + EN RW G Shapewriter on the iPhone: from the laboratory to the real world Design methods & practice/designing for expression / Zhai, Shumin / Kristensson, Per Ola / Gong, Pengjun / Greiner, Michael / Peng, Shilei Allen / Liu, Liang Mico / Dunnigan, Anthony Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009 v.2 p.2667-2670

Keywords: iPhone, mobile, shapewriter, text input, touch screen

doi.acm.org/10.1145/1520340.1520380 ACM Digital Library

Summary: We present our experience in bringing ShapeWriter, a novel HCI research product, from the laboratory to real world users through iPhone's App Store.

= ^ + EN RW G Usable intelligent interactive systems: CHI 2009 special interest group meeting Special interest groups / Spaulding, Aaron / Gajos, Krzysztof Z. / Jameson, Anthony / Kristensson, Per Ola / Bunt, Andrea / Haines, Will Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems 2009 v.2 p.2743-2746

Keywords: artificial intelligence, human computer interaction

doi.acm.org/10.1145/1520340.1520396 ACM Digital Library

Summary: The AI and HCI communities have often been characterized as having opposing views of how humans and computers should interact" observes Winograd in Shifting Viewpoints. It is time to narrow this gap. What was once considered the forefront of artificial intelligence (AI) research can now be found in commercial products. While some have failed, others, such as face detection in digital cameras or product recommendation systems, have become so mainstream they are no longer thought of as artificial intelligence. This special interest group provides a forum to examine the apparent gap between HCI and AI communities, to explore how intelligent technologies can enable novel interaction with computation, and to investigate the challenges associated with understanding human abilities, limitations, and preferences in order to drive the design of intelligent interactive systems.

= ^ + EN RW G Parakeet: a continuous speech recognition system for mobile touch-screen devices Mobile interaction / Vertanen, Keith / Kristensson, Per Ola Proceedings of the 2009 International Conference on Intelligent User Interfaces 2009 p.237-246

Keywords: continuous speech recognition, error correction, mobile text entry, predictive keyboard, speech input, text input, touch-screen interface, word confusion network

doi.acm.org/10.1145/1502650.1502685 ACM Digital Library

Summary: We present Parakeet, a system for continuous speech recognition on mobile touch-screen devices. The design of Parakeet was guided by computational experiments and validated by a user study. Participants had an average text entry rate of 18 words-per-minute (WPM) while seated indoors and 13 WPM while walking outdoors. In an expert pilot study, we found that speech recognition has the potential to be a highly competitive mobile text entry method, particularly in an actual mobile setting where users are walking around while entering text.

= ^ + EN RW G Parakeet: a demonstration of speech recognition on a mobile touch-screen device Demonstrations / Vertanen, Keith / Kristensson, Per Ola Proceedings of the 2009 International Conference on Intelligent User Interfaces 2009 p.483-484

Keywords: error correction, mobile continuous speech recognition, speech input, touch-screen interface, word confusion network

doi.acm.org/10.1145/1502650.1502726 ACM Digital Library

Summary: We demonstrate Parakeet -- a continuous speech recognition system for mobile touch-screen devices. Parakeet's interface is designed to make correcting errors easy on a handheld device while on the move. Users correct errors using a touch-screen to either select alternative words from a word confusion network or by typing on a predictive software keyboard. Our interface design was guided by computational experiments. We conducted a user study to validate our design. We found novices entered text at 18 WPM while seated indoors and 13 WPM while walking outdoors.

= ^ + EN RW G Interlaced QWERTY: accommodating ease of visual search and input flexibility in shape writing Post-QWERTY QWERTY / Zhai, Shumin / Kristensson, Per Ola Proceedings of ACM CHI 2008 Conference on Human Factors in Computing Systems 2008 v.1 p.593-596

doi.acm.org/10.1145/1357054.1357149 ACM Digital Library

Summary: Shape writing is an input technology for touch-screen mobile phones and pen-tablets. To shape write text, the user spells out word patterns by sliding a finger or stylus over a graphical keyboard. The user's trace is then recognized by a pattern recognizer. In this paper we analyze and evaluate various keyboard layouts, including alphabetic, optimized (ATOMIK), QWERTY, and interlaced QWERTY for shape writing. The goodness of a layout for shape writing has two aspects. For users' initial ease of use the letters should be easy to visually locate. For long term use, however, the layout should maximize the imprecision tolerance and writing flexibility for all words. We present empirical studies for the former and mathematical analyses for the latter. Our results led to a new layout, interlaced QWERTY, which offers excellent separation of word shapes, while still maintaining a low visual search time. Many of the findings in our study also apply to traditional soft keyboards tapped with a stylus or one finger.

= ^ + EN RW G On the benefits of confidence visualization in speech recognition Visualizations / Vertanen, Keith / Kristensson, Per Ola Proceedings of ACM CHI 2008 Conference on Human Factors in Computing Systems 2008 v.1 p.1497-1500

doi.acm.org/10.1145/1357054.1357288 ACM Digital Library

Summary: In a typical speech dictation interface, the recognizer's best-guess is displayed as normal, unannotated text. This ignores potentially useful information about the recognizer's confidence in its recognition hypothesis. Using a confidence measure (which itself may sometimes be inaccurate), we investigated providing visual feedback about low-confidence portions of the recognition using shaded, red underlining. An evaluation showed, compared to a baseline without underlining, underlining low-confidence areas did not increase user's speed or accuracy in detecting errors. However, we found that when recognition errors were correctly underlined, they were discovered significantly more often than baseline. Conversely, when errors failed to be underlined, they were discovered less often. Our results indicate confidence visualization can be effective -- but only if the confidence measure has high accuracy. Further, since our results show that users tend to trust confidence visualization, designers should be careful in its application if a high accuracy confidence measure is not available.

= ^ + EN RW G Improving word-recognizers using an interactive lexicon with active and passive words Short papers / Kristensson, Per Ola / Zhai, Shumin Proceedings of the 2008 International Conference on Intelligent User Interfaces 2008 p.353-356

doi.acm.org/10.1145/1378773.1378828 ACM Digital Library

Summary: The words a user is likely to write comprise the user's active vocabulary. This vocabulary is considerably smaller than the passive vocabulary of words a user reads. We explore an interactive adaptive lexicon method that separates a large lexicon into active and passive sets, and gradually expands and adapts the active set to reflect the user's active vocabulary. The adaptation is achieved through lightweight interaction as a by product of actual use. The effectiveness of the technique is demonstrated through a computational experiment and a user study.

= ^ + EN RW G InfoTouch: an explorative multi-touch visualization interface for tagged photo collections Short papers / Kristensson, Per Ola / Arnell, Olof / Björk, Annelie / Dahlbäck, Nils / Pennerup, Joackim / Prytz, Erik / Wikman, Johan / Åström, Niclas Proceedings of the Fifth Nordic Conference on Human-Computer Interaction 2008 p.491-494

Keywords: information visualization, interaction surfaces, multi-touch, photo browsing, photo collections, tag clouds, tagging, tags, visualization

doi.acm.org/10.1145/1463160.1463227 ACM Digital Library

Summary: We report on a design exploration into how a large multi-touch tabletop display can be used for information visualization. We designed an interface where users explored a tagged photo collection by bi-manual manipulation of the collections' tag cloud. User feedback showed that despite the availability of multi-touch most of the actual interactions were single-touch. However, some particular natural actions, such as grabbing the tag cloud and partitioning it into two parts, were often carried with both hands. Thus our user study indicates that multi-touch can act as a useful complementary interaction method in information visualization interfaces.

= ^ + EN RW G Command strokes with and without preview: using pen gestures on keyboard for command selection Novel navigation / Kristensson, Per Ola / Zhai, Shumin Proceedings of ACM CHI 2007 Conference on Human Factors in Computing Systems 2007 v.1 p.1137-1146

doi.acm.org/10.1145/1240624.1240797 ACM Digital Library

Summary: This paper presents a new command selection method that provides an alternative to pull-down menus in pen-based mobile interfaces. Its primary advantage is the ability for users to directly select commands from a very large set without the need to traverse menu hierarchies. The proposed method maps the character strings representing the commands onto continuous pen-traces on a stylus keyboard. The user enters a command by stroking part of its character string. We call this method "command strokes." We present the results of three experiments assessing the usefulness of the technique. The first experiment shows that command strokes are 1.6 times faster than the de-facto standard pull-down menus and that users find command strokes more fun to use. The second and third experiments investigate the effect of displaying a visual preview of the currently recognized command while the user is still articulating the command stroke. These experiments show that visual preview does not slow users down and leads to significantly lower error rates and shorter gestures when users enter new unpracticed commands.

= ^ + EN RW G Hard lessons: effort-inducing interfaces benefit spatial learning Learning / Cockburn, Andy / Kristensson, Per Ola / Alexander, Jason / Zhai, Shumin Proceedings of ACM CHI 2007 Conference on Human Factors in Computing Systems 2007 v.1 p.1571-1580

doi.acm.org/10.1145/1240624.1240863 ACM Digital Library

Summary: Interface designers normally strive for a design that minimises the user's effort. However, when the design's objective is to train users to interact with interfaces that are highly dependent on spatial properties (e.g. keypad layout or gesture shapes) we contend that designers should consider explicitly increasing the mental effort of interaction. To test the hypothesis that effort aids spatial memory, we designed a "frost-brushing" interface that forces the user to mentally retrieve spatial information, or to physically brush away the frost to obtain visual guidance. We report results from two experiments using virtual keypad interfaces -- the first concerns spatial location learning of buttons on the keypad, and the second concerns both location and trajectory learning of gesture shape. The results support our hypothesis, showing that the frost-brushing design improved spatial learning. The participants' subjective responses emphasised the connections between effort, engagement, boredom, frustration, and enjoyment, suggesting that effort requires careful parameterisation to maximise its effectiveness.

= ^ + EN RW G Learning shape writing by game playing Interactivity / Kristensson, Per Ola / Zhai, Shumin Proceedings of ACM CHI 2007 Conference on Human Factors in Computing Systems 2007 v.2 p.1971-1976

doi.acm.org/10.1145/1240866.1240934 ACM Digital Library

Summary: We present a computer game designed to efficiently and playfully teach users shape writing -- a new text entry method for pen-based devices.

= ^ + @ EN RW G In search of effective text input interfaces for off the desktop computing ARTICLE / Zhai, Shumin / Kristensson, Per-Ola / Smith, Barton A. Interacting with Computers 2005 v.17 n.3 p.229-250

Keywords: Text input; Pervasive; Mobile; Off-desktop computing; Shorthand; Gesture; Stylus; Virtual keyboard

dx.doi.org/10.1016/j.intcom.2003.12.007

Summary: It is generally recognized that today's frontier of HCI research lies beyond the traditional desktop computers whose GUI interfaces were built on the foundation of display -- pointing device -- full keyboard. Many interface challenges arise without such a physical UI foundation. Text writing -- ranging from entering URLs and search queries, filling forms, typing commands, to taking notes and writing emails and chat messages -- is one of the hard problems awaiting for solutions in off-desktop computing. This paper summarizes and synthesizes a research program on this topic at the IBM Almaden Research Center. It analyzes various dimensions that constitute a good text input interface; briefly reviews related literature; discusses the evaluation methodology issues of text input; presents the major ideas and results of two systems, ATOMIK and SHARK; and points out current and future directions in the area from our current vantage point.

= ^ + EN RW G Relaxing stylus typing precision by geometric pattern matching Long papers: natural language and gestural input / Kristensson, Per-Ola / Zhai, Shumin Proceedings of the 2005 International Conference on Intelligent User Interfaces 2005 p.151-158

doi.acm.org/10.1145/1040830.1040867 ACM Digital Library

Summary: Fitts' law models the inherent speed-accuracy trade-off constraint in stylus typing. Users attempting to go beyond the Fitts' law speed ceiling will tend to land the stylus outside the targeted key, resulting in erroneous words and increasing users' frustration. We propose a geometric pattern matching technique to overcome this problem. Our solution can be used either as an enhanced spell checker or as a way to enable users to escape the Fitts' law constraint in stylus typing, potentially resulting in higher text entry speeds than what is currently theoretically modeled. We view the hit points on a stylus keyboard as a high resolution geometric pattern. This pattern can be matched against patterns formed by the letter key center positions of legitimate words in a lexicon. We present the development and evaluation of an "elastic" stylus keyboard capable of correcting words even if the user misses all the intended keys, as long as the user's tapping pattern is close enough to the intended word.

= ^ + EN RW G Breaking the laws of action in the user interface Doctoral consortium / Kristensson, Per-Ola Proceedings of ACM CHI 2005 Conference on Human Factors in Computing Systems 2005 v.2 p.1120-1121

doi.acm.org/10.1145/1056808.1056841 ACM Digital Library

Summary: Fitts' law, Steering law and Law of crossing, collectively known as the laws of action, model the speed-accuracy trade-offs in common hci tasks. These laws impose a certain speed ceiling on precise actions in a user interface. My hypothesis is that for some interfaces, the constraints of these laws can be relaxed by using context information of the task. To support this thesis, I present two systems I have developed for pen-based text input on stylus keyboards. These systems break either Fitts' law or the Law of crossing by taking advantage of high-resolution information from the pen, and the fact that words can be seen as patterns traced on the keyboard. Using these systems users can potentially gain higher text entry speed than on a regular stylus keyboard that is limited by the laws of action. I conclude by discussing planned future research, primarily improved visual feedback and empirical evaluation.

= ^ + EN RW G SHARK²: a large vocabulary shorthand writing system for pen-based computers Gestures / Kristensson, Per-Ola / Zhai, Shumin Proceedings of the ACM Symposium on User Interface Software and Technology 2004 p.43-52

doi.acm.org/10.1145/1029632.1029640 ACM Digital Library

Summary: Zhai and Kristensson (2003) presented a method of speed-writing for pen-based computing which utilizes gesturing on a stylus keyboard for familiar words and tapping for others. In SHARK²:, we eliminated the necessity to alternate between the two modes of writing, allowing any word in a large vocabulary (e.g. 10,000-20,000 words) to be entered as a shorthand gesture. This new paradigm supports a gradual and seamless transition from visually guided tracing to recall-based gesturing. Based on the use characteristics and human performance observations, we designed and implemented the architecture, algorithms and interfaces of a high-capacity multi-channel pen-gesture recognition system. The system's key components and performance are also reported.

= ^ + EN RW G Shorthand writing on stylus keyboard Input interaction / Zhai, Shumin / Kristensson, Per-Ola Proceedings of ACM CHI 2003 Conference on Human Factors in Computing Systems 2003 v.1 p.97-104

doi.acm.org/10.1145/642611.642630 ACM Digital Library

Summary: We propose a method for computer-based speed writing, SHARK (shorthand aided rapid keyboarding), which augments stylus keyboarding with shorthand gesturing. SHARK defines a shorthand symbol for each word according to its movement pattern on an optimized stylus keyboard. The key principles for the SHARK design include high efficiency stemmed from layout optimization, duality of gesturing and stylus tapping, scale and location independent writing, Zipf's law, and skill transfer from tapping to shorthand writing due to pattern consistency. We developed a SHARK system based on a classic handwriting recognition algorithm. A user study demonstrated the feasibility of the SHARK method.