topauthor: Cao_Y* : Human-Computer Interaction Bibliography Search

[1] A Market in Your Social Network: The Effects of Extrinsic Rewards on Friendsourcing and Relationships Social Media Engagement / Zhu, Haiyi / Das, Sauvik / Cao, Yiqun / Yu, Shuang / Kittur, Aniket / Kraut, Robert Proceedings of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.1 p.598-609

ACM Digital Library Link

Summary: Friendsourcing consists of broadcasting questions and help requests to friends on social networking sites. Despite its potential value, friendsourcing requests often fall on deaf ears. One way to improve response rates and motivate friends to undertake more effortful tasks may be to offer extrinsic rewards, such as money or a gift, for responding to friendsourcing requests. However, past research suggests that these extrinsic rewards can have unintended consequences, including undermining intrinsic motivations and undercutting the relationship between people. To explore the effects of extrinsic reward on friends' response rate and perceived relationship, we conducted an experiment on a new friendsourcing platform -- Mobilyzr. Results indicate that large extrinsic rewards increase friends' response rates without reducing the relationship strength between friends. Additionally, the extrinsic rewards allow requesters to explain away the failure of friendsourcing requests and thus preserve their perceptions of relationship ties with friends.

[2] Ringteraction: Coordinated Thumb-index Interaction Using a Ring Late-Breaking Works: Novel Interactions / Ghosh, Sarthak / Kim, Hyeong Cheol / Cao, Yang / Wessels, Arne / Perrault, Simon T. / Zhao, Shengdong Extended Abstracts of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.2 p.2640-2647

ACM Digital Library Link

Summary: The thumb has the unique property of being opposable to the other fingers and is thus used to perform specific tasks such as grasping objects, which cannot be done otherwise. In this paper we present an interactive ring that takes advantage of this biomechanical advantage, by enabling thumb-index interaction. We propose a set of gestures involving the coordinated movement of the thumb against the proximal phalanx of the index finger that we call bi-digit interaction. Further, we present several scenarios where performing bi-digit interaction is quick, easy and advantageous for users.

[3] Assisting Food Journaling with Automatic Eating Detection Late-Breaking Works: Usable, Useful, and Desirable / Ye, Xu / Chen, Guanling / Gao, Yang / Wang, Honghao / Cao, Yu Extended Abstracts of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.2 p.3255-3262

ACM Digital Library Link

Summary: In this work we study the feasibility and usability of an assistive food journaling system that sends users just-in-time reminders when unique hand gestures during food consumption are detected using a smartwatch. Our study shows that participants were able to sustain food logging throughout a 2-week period with the help of our eating detection system, as the number of reminders correlate well with the number of food logs. Despite the fact that participants were required to wear the watch on their dominant hand, it was still quite usable and did not interfere with their normal activities. Participant feedback provided additional insights to inform future work to increase detection accuracy, reduce detection delay, and allow for more dietary logging features in the app.

[4] Lingo: Linearized Grassmannian Optimization for Nuclear Norm Minimization Session 4D: Optimization / Li, Qian / Niu, Wenjia / Li, Gang / Cao, Yanan / Tan, Jianlong / Guo, Li Proceedings of the 2015 ACM Conference on Information and Knowledge Management 2015-10-19 p.801-809

ACM Digital Library Link

Summary: As a popular heuristic to the matrix rank minimization problem, nuclear norm minimization attracts intensive research attentions. Matrix factorization based algorithms can reduce the expensive computation cost of SVD for nuclear norm minimization. However, most matrix factorization based algorithms fail to provide the theoretical guarantee for convergence caused by their non-unique factorizations. This paper proposes an efficient and accurate Linearized Grassmannian Optimization (Lingo) algorithm, which adopts matrix factorization and Grassmann manifold structure to alternatively minimize the subproblems. More specially, linearization strategy makes the auxiliary variables unnecessary and guarantees the close-form solution for low per-iteration complexity. Lingo then converts linearized objective function into a nuclear norm minimization over Grassmannian manifold, which could remedy the non-unique of solution for the low-rank matrix factorization. Extensive comparison experiments demonstrate the accuracy and efficiency of Lingo algorithm. The global convergence of Lingo is guaranteed with theoretical proof, which also verifies the effectiveness of Lingo.

[5] Scented Pebbles: Interactive Ambient Experience with Smell and Lighting Art Exhibition / Cao, Yan Yan / Okude, Naohito Proceedings of the 2015 International Conference on Tangible and Embedded Interaction 2015-01-15 p.409-410

ACM Digital Library Link

Summary: Scented Pebbles is a collection of interactive lighting objects to create multisensory ambience of light and smell. When it senses people's movement and touch, the networked objects will generate dynamic ambience. The pebbles emit smells and control the lighting conditions to create your unique ambience such as Hawaiian Sunset or Japanese Onsen. Experience the orchestra of smell and light play and let your mind run free. The paper presented interactive approach to evoke sensorial imagination through multisensory interactions including olfactory sense.

[6] Examining WeChat users' motivations, trust, attitudes, and positive word-of-mouth: Evidence from China / Lien, Che Hui / Cao, Yang Computers in Human Behavior 2014-12 v.41 n.0 p.104-111

Keywords: Motivation

Keywords: Trust

Keywords: Attitude

Keywords: Word-of-mouth

Keywords: Social networking site

Link to Article at sciencedirect

Summary: WeChat is a mobile instant text and voice messaging communication service and has become an important social media platform in China. The objectives of this article are to examine the effects of psychological motivations (entertainment, sociality, and information) and trust on WeChat users' attitudes and to assess the influence of users' attitudes and their trust on positive word-of-mouth. This study represents one of the few that empirically investigates WeChat users' motives, attitudes, trust, and their associated behavior. The research model was tested using data randomly collected from the database of Sojump. The numbers of valid observations were 264. Structure equation modeling was employed to verify and validate the research model. The outcomes confirm the path effects showing that entertainment, sociality, information, and trust positively influence WeChat users' attitudes and users' trust and their attitudes significantly affect positive WOM. The research results provide insight into how WeChat can motivate users and build their trust to improve their attitudes which in turn will increase WeChat users' willingness in making positive comments on products and services.

[7] A Robust Panel Extraction Method for Manga Posters 3 / Pang, Xufang / Cao, Ying / Lau, Rynson W. H. / Chan, Antoni B. Proceedings of the 2014 ACM International Conference on Multimedia 2014-11-03 p.1125-1128

ACM Digital Library Link

Summary: Automatically extracting frames/panels from digital comic pages is crucial for techniques that facilitate comic reading on mobile devices with limited display areas. However, automatic panel extraction for manga, i.e., Japanese comics, can be especially challenging, largely because of its complex panel layout design mixed with various visual symbols throughout the page. In this paper, we propose a robust method for automatically extracting panels from digital manga pages. Our method first extracts the panel block by closing open panels and identifying a page background mask. It then performs a recursive binary splitting to partition the panel block into a set of sub-blocks, where an optimal splitting line at each recursive level is determined adaptively.

[8] Continuance use intention of enterprise instant messaging: a knowledge management perspective / Ajjan, Haya / Hartshorne, Richard / Cao, Yingxia / Rodriguez, Michael Behaviour and Information Technology 2014-07-03 v.33 n.7 p.678-692

Link to Article at Taylor & Francis

Summary: Instant messaging has been widely utilised by a variety of types of organisations to improve the efficiency and effectiveness of internal communication and knowledge management (KM). To date, though, the continuance use of enterprise instant messaging (EIM) and its impact on KM outcomes have not been well understood in both academia and practice. This paper uses the decomposed theory of planned behaviour to explore factors that influence continual usage of EIM applications within organisations, as well as the impact of the continuance use decisions on knowledge creation, transfer, and retention within organisations. Our results are useful in developing guidelines and strategies to increase the likelihood of the continuance use of EIM and to improve the potential outcome of its use within organisations.

[9] Research on Behavioral Semanteme Form Based on Early Education Products The Design of Everyday Things / Cao, Ying / Lei, Tian / Wu, Xun HCI International 2014: 16th International Conference on HCI: Posters' Extended Abstracts, Part I 2014-06-22 v.4 p.134-138

Keywords: Product semantics States; Behavioral semantics States; user experience

Link to Digital Content at Springer

Summary: Currently, there are a variety of the early education products in the market. A strict approach for classification of these products, however, is generally absent. But even so, any kind of the early education products are indeed built on the same principle that almost all devisers are making attempts to attract users for participation and experience from the three aspects -- the visual sense, the auditory sense and the sense of touch. The way for experience is also limited to some certain operant behavior including "press", "twist" and "thump". Due to the fact that young children are the targeted users for the early education products and because of their unique characteristics -- the so-called "realistic feature" embedded into their intelligence, their behavioral norms are conspicuously distinguishing from adults. It is therefore that the development of related products should not be conducted in the logical way of adults. It is proper to cultivate the cognitive ability, judgment and logics of infants in a simplistic and pleasant context and circumstances.
This research will delve into behavior from a perspective of Semantics by initiating a study on "Form", which is the carrier for products' semanteme. Experimental data of a series of early education products will be reviewed for reference and for making contributions to the quantitative research on the influence of forms on behavior. Three key concepts, which are the "form", the "semanteme" and the "behavior", will also be effectively integrated into and contributing to the two new concepts, the "Behavioral Semanteme Form" and the "Semanteme Form Model". The research aims at providing the entire and detailed explanations to the formation, structural characteristics and category of the semanteme by adopting the operable and controllable approaches.

[10] Gestures: The Reformer of the User's Mental Model in Mobile HCI Design for Novel Interaction Techniques and Realities / Lei, Tian / Xiong, Luyao / Chen, Kun / Liu, Xu / Cao, Yin / Zhang, Qi / Liu, Dongyuan / Guo, Sisi DUXU 2014: Third International Conference on Design, User Experience, and Usability, Part II: User Experience Design for Diverse Interaction Platforms and Environments 2014-06-22 v.2 p.586-597

Keywords: spatial consistency; direction of gesture; user experience; mobile usability

Link to Digital Content at Springer

Summary: This paper, by making a usability testing of four Chinese mainstream apps, finds that the mental model's spatial consistency can directly affect the mobile performance. Meanwhile, it also finds that in the touch-screen environment, the concept of direction is ignored by the app users when they construct mental models. Further experimental studies show that: 1) mental model's spatial consistency and Gestalt can influence the gesture's direction, and the Gestalt's impact on it is stronger than that of mental models; 2) in performance the subjects have ignored the time's growth caused by the misdirected gestures, and the completion time is no longer an evaluation criteria for the satisfaction; 3) information type significantly affects completion time, and the hints produced by the continuity of the information content do not influence the direction of gesture; 4) the difference of interaction devices is actually the reason that a user notices the direction or not.

[11] The (un)supervised detection of overlapping communities as well as hubs and outliers via (Bayesian) NMF WWW 2014 posters / Cao, Xiaochun / Wang, Xiao / Jin, Di / Cao, Yixin / He, Dongxiao Companion Proceedings of the 2014 International Conference on the World Wide Web 2014-04-07 v.2 p.233-234

ACM Digital Library Link

Summary: The detection of communities in various networks has been considered by many researchers. Moreover, it is preferable for a community detection method to detect hubs and outliers as well. This becomes even more interesting and challenging when taking the unsupervised assumption, that is, we do not assume the prior knowledge of the number K of communities. In this poster, we define a novel model to identify overlapping communities as well as hubs and outliers. When K is given, we propose a normalized symmetric nonnegative matrix factorization algorithm to learn the parameters of the model. Otherwise, we introduce a Bayesian symmetric nonnegative matrix factorization to learn the parameters of the model, while determining K. Our experiment indicate its superior performance on various networks.

[12] Combining geographical information of users and content of items for accurate rating prediction WWW 2014 posters / Qiao, Zhi / Zhang, Peng / He, Jing / Cao, Yanan / Zhou, Chuan / Guo, Li Companion Proceedings of the 2014 International Conference on the World Wide Web 2014-04-07 v.2 p.361-362

ACM Digital Library Link

Summary: Recommender systems have attracted attentions lately due to their wide and successful applications in online advertising. In this paper, we propose a Bayesian generative model to describe the generative process of rating, which combines geographical information of users and content of items. The generative model consists of two interacting LDA models, where one LDA model for location-based user groups (user dimension) and the other for the topics of content of items (item dimension). A Gibbs sampling algorithm is proposed for parameter estimation. Experiments have shown our proposed method outperforms baseline methods.

[13] Personalized influence maximization on social networks KM track: social networks (1) / Guo, Jing / Zhang, Peng / Zhou, Chuan / Cao, Yanan / Guo, Li Proceedings of the 2013 ACM Conference on Information and Knowledge Management 2013-10-27 p.199-208

ACM Digital Library Link

Summary: In this paper, we study a new problem on social network influence maximization. The problem is defined as, given a target user $w$, finding the top-k most influential nodes for the user. Different from existing influence maximization works which aim to find a small subset of nodes to maximize the spread of influence over the entire network (i.e., global optima), our problem aims to find a small subset of nodes which can maximize the influence spread to a given target user (i.e., local optima). The solution is critical for personalized services on social networks, where fully understanding of each specific user is essential. Although some global influence maximization models can be narrowed down as the solution, these methods often bias to the target node itself. To this end, in this paper we present a local influence maximization solution. We first provide a random function, with low variance guarantee, to randomly simulate the objective function of local influence maximization. Then, we present efficient algorithms with approximation guarantee. For online social network applications, we also present a scalable approximate algorithm by exploring the local cascade structure of the target user. We test the proposed algorithms on several real-world social networks. Experimental results validate the performance of the proposed algorithms.

[14] An Interface Design Method for E-commerce Sites' Homepage Considering Users' Emotions Digital Human Modeling and Ergonomics in Working Environments / Guo, Fu / Cao, Yaqin / Wang, Meng / Ding, Yi / Liu, Lin Wei DHM 2013: 4th International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics, and Risk Management, Part II: Human Body Modeling and Ergonomics 2013-07-21 v.2 p.30-39

Keywords: E-commerce; Emotion; Kansei engineering; Web design; PLS

Link to Digital Content at Springer

Summary: This paper proposes a useful method to understand the relationship between web design elements, Kansei evaluation and users' emotions based on Kansei Engineering, taking E-commerce sites for example. Firstly it establishes customers' evaluation image words through a survey of the web interface preference. Then it collects the data of Kansei evaluation and users' emotions to different websites by an emotion assessment test. Lastly it builds the relation models between web design elements, Kansei evaluation and users' emotions using the quantification theory I and partial least squares (PLS) method, and confirms the validity of the models.

[15] A Practical Mobile Dry EEG System for Human Computer Interfaces Applications of Augmented Cognition / Chi, Yu M. / Wang, Yijun / Wang, Yu-Te / Jung, Tzyy-Ping / Kerth, Trevor / Cao, Yuchen FAC 2013: 7th International Conference on Foundations of Augmented Cognition 2013-07-21 p.649-655

Link to Digital Content at Springer

Summary: A complete mobile electroencephalogram (EEG) system based on a novel, flexible dry electrode is presented. The wireless device features 32-channels in a soft, adjustable headset. Integrated electronics enable high resolution (24-bit, 250 samples/sec) acquisition electronics and can acquire operate for more than four hours on a single AAA battery. The system weighs only 140 g and is specifically optimized for ease of use. After training users can self-don the headset in around three minutes. Test data on multiple subjects with simultaneously acquired EEGs from a traditional wet, wired system show a very high degree of signal correlation in AEP and P300 tasks.

[16] An error driven approach to query segmentation Posters: search systems and applications / Zhang, Wei / Cao, Yunbo / Lin, Chin-Yew / Su, Jian / Tan, Chew-Lim Companion Proceedings of the 2013 International Conference on the World Wide Web 2013-05-13 v.2 p.127-128

ACM Digital Library Link

Summary: Query segmentation is the task of splitting a query into a sequence of non-overlapping segments that completely cover all tokens in the query. The majority of query segmentation methods are unsupervised. In this paper, we propose an error-driven approach to query segmentation (EDQS) with the help of search logs, which enables unsupervised training with guidance from the system-specific errors. In EDQS, we first detect the system's errors by examining the consistency among the segmentations of similar queries. Then, a model is trained by the detected errors to select the correct segmentation of a new query from the top-n outputs of the system. Our evaluation results show that EDQS can significantly boost the performance of state-of-the-art query segmentation methods on a publicly available data set.

[17] Does Context Matter? The Impact of Use Context on Mobile Internet Adoption / Yang, Shuiqing / Lu, Yaobin / Gupta, Sumeet / Cao, Yuzhi International Journal of Human-Computer Interaction 2012-08 v.28 n.8 p.530-541

Link to Article at Taylor & Francis

Summary: Consumers' perceived value plays a dominant role in determining the adoption of mobile technologies. However, behavior literature suggests that consumer value is context dependent. The current study attempts to understand the effects of use context on consumers' perceived value and adoption of mobile Internet. An adoption model that reflects the unique use context and the utilitarian values (perceived usefulness and perceived mobility) and hedonic values (perceived enjoyment and concentration) of mobile Internet was developed and empirically tested against data collected from 507 mobile Internet users in China. Structural equation analysis results indicate that consumers' values perceptions and adoption decisions are context dependent. The use context fully mediates the effects of utilitarian values and partially mediates the relationship between hedonic values and intention to use mobile Internet. Theoretical and practical implications of the findings are discussed.

[18] Distributed graph pattern matching Data and content management 2 / Ma, Shuai / Cao, Yang / Huai, Jinpeng / Wo, Tianyu Proceedings of the 2012 International Conference on the World Wide Web 2012-04-16 v.1 p.949-958

ACM Digital Library Link

Summary: Graph simulation has been adopted for pattern matching to reduce the complexity and capture the need of novel applications. With the rapid development of the Web and social networks, data is typically distributed over multiple machines. Hence a natural question raised is how to evaluate graph simulation on distributed data. To our knowledge, no such distributed algorithms are in place yet. This paper settles this question by providing evaluation algorithms and optimizations for graph simulation in a distributed setting. (1) We study the impacts of components and data locality on the evaluation of graph simulation. (2) We give an analysis of a large class of distributed algorithms, captured by a message-passing model, for graph simulation. We also identify three complexity measures: visit times, makespan and data shipment, for analyzing the distributed algorithms, and show that these measures are essentially controversial with each other. (3) We propose distributed algorithms and optimization techniques that exploit the properties of graph simulation and the analyses of distributed algorithms. (4) We experimentally verify the effectiveness and efficiency of these algorithms, using both real-life and synthetic data.

[19] Mobile payment services adoption across time: An empirical study of the effects of behavioral beliefs, social influences, and personal traits / Yang, Shuiqing / Lu, Yaobin / Gupta, Sumeet / Cao, Yuzhi / Zhang, Rui Computers in Human Behavior 2012-01 v.28 n.1 p.129-142

Keywords: Social influences

Keywords: Personal traits

Keywords: Behavioral beliefs

Keywords: Mobile payment services

Keywords: Potential adopters

Keywords: Current users

Link to Article at sciencedirect

Summary: Mobile payment is an emerging and important application of mobile commerce. The adoption and use of mobile payment services are critical for both service providers and investors to profit from such an innovation. The present study attempts to identify the determinants of pre-adoption of mobile payment services and explore the temporal evolution of these determinants across the pre-adoption and post-adoption stages from a holistic perspective including behavioral beliefs, social influences, and personal traits. A research model that reflects the characteristics and usage contexts of mobile payment services is developed and empirically tested by using structural equation modeling on datasets consisting of 483 potential adopters and 156 current users of a mobile payment service in China. Our findings show that behavioral beliefs in combination with social influences and personal traits are all important determinants for mobile payment services adoption and use, but their impacts on behavioral intention do vary across in different stages. Theoretical and practical implications of the findings are presented.

[20] Eliciting risk perceptions with an online game: preliminary results Interactive presentations / McGill, William L. / Cao, Yan / Jiang, Miao / Calle, Jorge J. / Broomell, Stephen / Lauser, Gale Proceedings of ACM CSCW'11 Conference on Computer-Supported Cooperative Work 2011-03-19 p.681-684

ACM Digital Library Link

Summary: We describe a scientific casual browser game called LinkIT for eliciting societal risk perceptions in the form of mental models represented as influence diagrams. Given this knowledge, we can highlight similarities and differences across demographic groups as well as compare individual responses with expert models. These comparisons inform how risk should be best communicated to resolve knowledge gaps and misperceptions. Here we introduce the LinkIT concept, present preliminary results and propose future work.

[21] A study on factors that affect users' behavioral intention to transfer usage from the offline to the online channel / Lu, Yaobin / Cao, Yuzhi / Wang, Bin / Yang, Shuiqing Computers in Human Behavior 2011-01 v.27 n.1 p.355-364

Keywords: Online banking service

Keywords: Usage transfer

Keywords: Valence framework

Keywords: Habit

Keywords: Innovativeness

Keywords: Internet experience

Link to Article at sciencedirect

Summary: Increasingly more service providers offer both offline and online services simultaneously, but consumers still seem to prefer using offline services rather than online ones. Our research focuses on factors that influence users' intention to transfer their usage from the offline to the online channel that offer similar services. Drawing on the valence framework and prior research related to habit, innovativeness, and Internet experience, we propose a research model that incorporates motivators and inhibitors of usage transfer from both the offline and online channels. Using banking services in China as the research context, our study reveals that innovativeness in new technology and relative benefit have positive effects on users' intention to transfer usage. Conversely, habits that consumers form in the offline channel have a negative effect on the intention to transfer usage. Moreover, our findings indicate that Internet experience moderates the relationship between relative benefit and consumers' intention to transfer usage from offline to online services. These results provide a better understanding of consumers' usage-transfer behavior and offer suggestions to providers in boosting their consumers' use of online services.

[22] Evaluating informative auditory and tactile cues for in-vehicle information systems Exploring modes of interaction / Cao, Yujia / van der Sluis, Frans / Theune, Mariët / Akker, Rieks op den / Nijholt, Anton AutomnotiveUI 2010: International Conference on Automotive User Interfaces and Interactive Vehicular Applications 2010-11-11 p.102-109

ACM Digital Library Link

Summary: As in-vehicle information systems are increasingly able to obtain and deliver information, driver distraction becomes a larger concern. In this paper we propose that informative interruption cues (IIC) can be an effective means to support drivers' attention management. As a first step, we investigated the design and presentation modality of IIC that conveyed not only the arrival but also the priority level of a message. Both sound and vibration cues were created for four different priority levels and tested in 5 task conditions that simulated possible perceptional and cognitive load in real driving situations. Results showed that the cues were quickly learned, reliably detected, and quickly and accurately identified. Vibration was found to be a promising alternative for sound to deliver IIC, as vibration cues were identified more accurately and interfered less with driving. Sound cues also had advantages in terms of shorter response time and more (reported) physical comfort.

[23] Automatic extraction of web data records containing user-generated content KM track: information extraction / Song, Xinying / Liu, Jing / Cao, Yunbo / Lin, Chin-Yew / Hon, Hsiao-Wuen Proceedings of the 2010 ACM Conference on Information and Knowledge Management 2010-10-26 p.39-48

ACM Digital Library Link

Summary: In this paper, we are concerned with the problem of automatically extracting web data records that contain user-generated content (UGC). In previous work, web data records are usually assumed to be well-formed with a limited amount of UGC, and thus can be extracted by testing repetitive structure similarity. However, when a web data record includes a large portion of free-format UGC, the similarity test between records may fail, which in turn results in lower performance. In our work, we find that certain domain constraints (e.g., post-date) can be used to design better similarity measures capable of circumventing the influence of UGC. In addition, we also use anchor points provided by the domain constraints to improve the extraction process, which ends in an algorithm called MiBAT (Mining data records Based on Anchor Trees). We conduct extensive experiments on a dataset consisting of forum thread pages which are collected from 307 sites that cover 219 different forum software packages. Our approach achieves a precision of 98.9% and a recall of 97.3% with respect to post record extraction. On page level, it perfectly handles 91.7% of pages without extracting any wrong posts or missing any golden posts. We also apply our approach to comment extraction and achieve good results as well.

[24] Local danger warnings for drivers: the effect of modality and level of assistance on driver reaction User-centered design / Cao, Yujia / Mahr, Angela / Castronovo, Sandro / Theune, Mariët / Stahl, Christoph / Müller, Christian A. Proceedings of the 2010 International Conference on Intelligent User Interfaces 2010-02-07 p.239-248

Keywords: automotive, car2car communication, multimodal interfaces

ACM Digital Library Link

Summary: Local danger warning is an important function of Advanced Driver Assistance Systems (ADAS) to improve the safety of driving. The user interface (the warning presentation) is particularly crucial to a successful danger avoidance. We present a user study investigating various warning presentations using a scenario of emergent road obstacles. Two presentation factors were selected: modality and level of assistance. The modality factor had 4 variants: speech warning, visual and speech warning, visual warning with blinking cue, and visual warning with sound cue. The level of assistance varied between with or without action suggestions (AS). In accordance with the ISO usability model, a total of 6 measurements were derived to assess the effectiveness and efficiency of the warnings and the drivers' satisfaction. Results indicate that the combination of speech and visual modality leads to the best performance as well as the highest satisfaction. In contrast, purely auditory and purely visual modalities were both insufficient for presenting high-priority warnings. AS generally improved the usability of the warnings especially when they were accompanied by supporting information so that drivers could validate the suggestions.

[25] Learning to recommend questions based on user ratings KM information filtering and recommender systems / Sun, Ke / Cao, Yunbo / Song, Xinying / Song, Young-In / Wang, Xiaolong / Lin, Chin-Yew Proceedings of the 2009 ACM Conference on Information and Knowledge Management 2009-11-02 p.751-758

ACM Digital Library Link

Summary: At community question answering services, users are usually encouraged to rate questions by votes. The questions with the most votes are then recommended and ranked on the top when users browse questions by category. As users are not obligated to rate questions, usually only a small proportion of questions eventually gets rating. Thus, in this paper, we are concerned with learning to recommend questions from user ratings of a limited size. To overcome the data sparsity, we propose to utilize questions without users rating as well. Further, as there exist certain noises within user ratings (the preference of some users expressed in their ratings diverges from that of the majority of users), we design a new algorithm called 'majority-based perceptron algorithm' which can avoid the influence of noisy instances by emphasizing its learning over data instances from the majority users. Experimental results from a large collection of real questions confirm the effectiveness of our proposals.