Psychophysiology of the passive user: Exploring the effect of technological conditions and personality traits

This purpose of this study was to investigate physiological response patterns of passive users versus active users under varying technological conditions. The relationship between user personality traits and physiological responses was also explored. In work systems, different types of users interact with technologies in different ways. Active users may control technologies, while passive users may watch the active user and the technology. While they are both important stakeholders in the system, little empirical research has been conducted to understand the passive users to date. A mixed design experiment was conducted to investigate passive user psychophysiological state, while active and passive users operated a technology under varying technological states (normal, unreliable, and difficult). Physiological measures were collected from passive users while technologies were being operated, these included electrodermal and cardiovascular (heart rate and heart rate variability). Results show that individual active users and passive users have distinct physiological response patterns in heart rate and heart rate variability while using the technology. Exploratory analyses indicated that conscientiousness was positively related to individual active users' task performance; openness, agreeableness, and extraversion were associated with passive users' electrodermal and cardiovascular responses. In addition, social interaction is more influential for passive users' physiological responses, compared to task performing. The effects of active and passive user personality traits on technology interactions are illustrated through distinctive physiological responses.Relevance to industryFindings from this study suggest that to improve passive user experience, systems that include both active and passive users should be designed to facilitate communication and information sharing between users.     

面向用户偏好建模的个性化对话推荐算法

推荐系统的目标是从物品数据库中，选择出与用户兴趣偏好相匹配的子集，缓解用户面临的“信息过载”问题。因而近年来推荐系统越来越多地应用到电商、社交等领域，展现出巨大的商业潜力。传统推荐系统中，系统对用户的认知往往来源于历史交互记录，例如点击率或者购买记录，这是一种隐式用户反馈。对话推荐系统能够通过自然语言与用户进行多轮对话，逐步深入挖掘其兴趣偏好，从而向对方提供高质量的推荐结果。相比于传统推荐系统，对话推荐系统主要有两方面的不同。其一，对话推荐系统能够利用自然语言与用户进行语义上连贯的多轮对话，提升了人机交互中的用户体验；其二，系统能够询问特定的问题直接获取用户的显式反馈，从而更深入地理解用户兴趣偏好，提供更可靠的推荐结果。目前已经有不少工作在不同的问题设定下对该领域进行了探索，然而尽管如此，这些工作仍仅局限于关注当前正在进行的对话，忽视了过去交互记录中蕴涵的丰富信息，导致对用户偏好建模的不充分。为了解决这个问题，本文提出了一个面向用户偏好建模的个性化对话推荐算法框架，通过双线性模型注意力机制与自注意力层次化编码结构进行用户偏好建模，从而完成对候选物品的排序与推荐。本文设计的模型结构能够在充分利用用户历史对话信息的同时，权衡历史对话与当前对话两类数据的重要性。丰富的用户相关信息来源使得推荐结果在契合用户个性化偏好的同时，更具备多样性，从而缓解“信息茧房”等现象带来的不良影响。基于公开数据集的实验表明了本文方法在个性化对话推荐任务上的有效性。     

Design of a Graphical User Interface for Process Control Based on the Example of a Paper Recycling Plant

The following article is the third of 3 articles that focus on user-centered design and usability in the field of industrial process control. Whereas the first article in this series (Burmester, Komischke, & Wust, this issue) dealt with usability engineering methods in the area of process control, this article explains the practical application of this procedure. To this end, a pilot project for the user-centered design of a user interface for a paper recycling plant is described here by way of example. Here a new layout based on users' mental models was systematically prepared. Extensive usability tests revealed that the design was understood and accepted both by users without any knowledge of the system (pupils at a paper technology college) and those with a knowledge of the system.     

对话推荐算法研究综述

推荐系统是一种通过理解用户的兴趣和偏好帮助用户过滤大量无效信息并获取感兴趣的信息或者物品的信息过滤系统.目前主流的推荐系统主要基于离线的、历史的用户数据,不断训练和优化线下模型,继而为在线的用户推荐物品,这类训练方式主要存在3个问题:基于稀疏且具有噪声的历史数据估计用户偏好的不可靠估计、对影响用户行为的在线上下文环境因素的忽略和默认用户清楚自身偏好的不可靠假设.由于对话系统关注于用户的实时反馈数据,获取用户当前交互的意图,因此“对话推荐”通过结合对话形式与推荐任务成为解决传统推荐问题的有效手段.对话推荐将对话系统实时交互的数据获取方式应用到推荐系统中,采用了与传统推荐系统不同的推荐思路,通过利用在线交互信息,引导和捕捉用户当前的偏好兴趣,并及时进行反馈和更新.在过去的几年里,越来越多的研究者开始关注对话推荐系统,这一方面归功于自然语言处理领域中语音助手以及聊天机器人技术的广泛使用,另一方面受益于强化学习、知识图谱等技术在推荐策略中的成熟应用.将对话推荐系统的整体框架进行梳理,将对话推荐算法研究所使用的数据集进行分类,同时对评价对话推荐效果的相关指标进行讨论,重点关注于对话推荐系统中的后...     

Experiments on user experiences with recommender interfaces

Recommender systems have been increasingly adopted as personalisation services in e-commerce. They facilitate users to locate items which they would be interested in viewing or purchasing. However, most studies have emphasised on the algorithm's performance, rather than on in-depth analysis of user experiences with the recommender interface. In this article, we report the results of two studies that compared two recommender interfaces: the organisation-based interface (where recommendations are presented in a category structure via the preference-based organisation method) and the standard ranked list (where recommendations are listed one after the other as ordered by their prediction scores).The first study focuses on evaluating users' eye-movement behaviour in these interfaces. With the help of an eye tracker, we found that the organisation interface (ORG) can significantly attract users' attentions to more recommended items. As a result, more users made product choices in that interface. The second, larger-scale, cross-cultural user survey further shows that the ORG performed significantly better in terms of enhancing users' perceived recommendation quality, perceived ease of use and perceived usefulness of the system. Hence, these empirical findings suggest that the change of recommender interface design can not only alter users' attention distribution, but also influence their subjective attitudes towards the system.     

A theoretical framework and empirical examination of the effects of foreign and translated interface language

Given the increased globalization and popularization of computer applications, translating a system's human interface into the local language has become a major consideration for software vendors and distributors. In this paper, we suggest a theoretical framework for the study of user interface translation. The framework includes recognizing vendors' and users' costs of, and benefits from, software translation. An experiment was conducted, based on this framework, to test user performance and preferences regarding interface translations. The experiment manipulated the translation of two interface components: documentation language and manipulation language. The results indicate that users are sensitive to different combinations of interface translation in a way that is commensurate with the instruction-following process (Terwilliger and Polson 1997). Users performed best when a fully translated interface was used and worst when only the manipulation language was translated. Users' preferences were in line with their performance, indicating that a cost benefit approach can serve as a promising starting point to the study of interface translation.     

Model-based automation of the design of user interfaces to digitalcontrol systems

Digital control systems, like those controlling the functions of buildings or industrial processes, pose a number of special problems for good user interface design. The general problems of providing usability, common to all systems, include difficulty in accessing and applying principles of good design. In addition, digital control systems can have multiple users, with multiple roles, and each installation has different configurations of systems, controls, and user interface devices. Providing interactions for the users of building control systems is often achieved by manually implementing each required display. This is an expensive solution, which often produces less than optimal results. We address these problems through the automation of user interface design. Our solution, called DIGBE (dynamic interface generation for building environments), separates the domain knowledge, interaction design, and presentation heuristics into multiple collaborating models. Each model contains knowledge about a particular aspect of interface design, and uses this knowledge to dynamically create each user interface that is needed to support the users of a control system. DIGBE demonstrates that it is possible to automatically and dynamically create consistent and individualized user interfaces from model-based design knowledge     

Using task analysis to improve usability of fatigue modelling software

The design of any interactive computer system requires consideration of both humans and machines. Software usability is one aspect of human–computer interaction that can benefit from knowledge of the user and their tasks. One set of methods for determining whether an application enables users to achieve their predetermined goals effectively and efficiently is task analysis. In the present study, a task analysis was applied to the graphical user interface of fatigue modelling software used in industry. The task analysis procedure allowed areas of usability improvement to be identified and then addressed with alternate interface prototypes. The present method of task analysis illustrates a practical and efficient way for software designers to improve software usability, user effectiveness and satisfaction, by involving users in the design process.     

Large high resolution displays for co-located collaborative sensemaking: Display usage and territoriality

From an exploratory user study using a fictional textual intelligence analysis task on a large, high-resolution vertical display, we investigated how pairs of users interact with the display to construct spatial schemas and externalize information, as well as how they establish shared and private territories. We investigated users' space management strategies depending on the design philosophy of the user interface (visualization- or document-centric). We classified the types of territorial behavior exhibited in terms of how the users interacted with information on the display (integrated or independent workspaces). Next, we examined how territorial behavior impacted the common ground between the pairs of users. Finally, we offer design suggestions for building future co-located collaborative visual analytics tools for use on large, high-resolution vertical displays.     

User Modeling for Adaptive News Access

We present a framework for adaptive news access, based on machine learning techniques specifically designed for this task. First, we focus on the system's general functionality and system architecture. We then describe the interface and design of two deployed news agents that are part of the described architecture. While the first agent provides personalized news through a web-based interface, the second system is geared towards wireless information devices such as PDAs (personal digital assistants) and cell phones. Based on implicit and explicit user feedback, our agents use a machine learning algorithm to induce individual user models. Motivated by general shortcomings of other user modeling systems for Information Retrieval applications, as well as the specific requirements of news classification, we propose the induction of hybrid user models that consist of separate models for short-term and long-term interests. Furthermore, we illustrate how the described algorithm can be used to address an important issue that has thus far received little attention in the Information Retrieval community: a user's information need changes as a direct result of interaction with information. We empirically evaluate the system's performance based on data collected from regular system users. The goal of the evaluation is not only to understand the performance contributions of the algorithm's individual components, but also to assess the overall utility of the proposed user modeling techniques from a user perspective. Our results provide empirical evidence for the utility of the hybrid user model, and suggest that effective personalization can be achieved without requiring any extra effort from the user.     

脑机接口辅助的动态目标选择技术

动态目标选择是现代交互界面中最为基础的交互任务之一,目前存在多种辅助技术,但这些技术的决策和参数设定有很强的经验性,无法根据用户的当前状态进行调整.为了解决这个问题,基于两个认知负荷与难度感知的假设,提出一种脑机接口辅助的动态目标选择技术,利用近红外光谱信号对用户认知负荷感知的敏感性,实时地调整目标选择技术参数,给不同用户个体提供个性化辅助,适用于不同场景、用户状态和任务难度.通过一组实验,对提出的假设进行了验证,并且基于该假设构建的脑机接口辅助的动态目标选择技术,较不作任何辅助和固定辅助技术两种方案都更优,具体地,在选择错误率上分别降低20.55%和12.09%,在完成时间上分别降低998.35ms和208.67ms.     

Exploiting behavioral user models for point of interest recommendation in smart museums

ABSTRACT

The Internet of Things (IoT) holds the promise to blend real-world and online behaviors in principled ways, yet we are only beginning to understand how to effectively exploit insights from the online realm into effective applications in smart environments. Such smart environments aim to provide an improved, personalized experience based on the trail of user interactions with smart devices, but how does recommendation in smart environments differ from the usual online recommender systems? And can we exploit similarities to truly blend behavior in both realms to address the fundamental cold-start problem? In this article, we experiment with behavioral user models based on interactions with smart devices in a museum, and investigate the personalized recommendation of what to see after visiting an initial set of Point of Interests (POIs), a key problem in personalizing museum visits or tour guides, and focus on a critical one-shot POI recommendation task—where to go next? We have logged users' onsite physical information interactions during visits in an IoT-augmented museum exhibition at scale. Furthermore, we have collected an even larger set of search logs of the online museum collection. Users in both sets are unconnected, for privacy reasons we do not have shared IDs. We study the similarities between users' online digital and onsite physical information interaction behaviors, and build new behavioral user models based on the information interaction behaviors in (i) the physical exhibition space, (ii) the online collection, or (iii) both. Specifically, we propose a deep neural multilayer perceptron (MLP) based on explicitly given users' contextual information, and set-based extracted features using users' physical information interaction behaviors and similar users' digital information interaction behaviors. Our experimental results indicate that the proposed behavioral user modeling approach, using both physical and online user information interaction behaviors, improves the onsite POI recommendation baselines' performances on all evaluation metrics. Our proposed MLP approach achieves 83% precision at rank 1 on the critical one-shot POI recommendation problem, realizing the high accuracy needed for fruitful deployment in practical situations. Furthermore, the MLP model is less sensitive to amount of real-world interactions in terms of the seen POIs set-size, by backing of to the online data, hence helps address the cold start problem in recommendation. Our general conclusion is that it is possible to fruitfully combine information interactions in the online and physical world for effective recommendation in smart environments.     

rIBIS: a real-time group hypertext system

This paper describes rIBIS, a real-time group hypertext system, which allows a distributed set of users to simultaneously browse and edit multiple views of a hypertext network. At any time, rIBIS users can switch back and forth between tightly coupled and loosely coupled interaction modes. The paper describes the high-level architecture and user interface of the rIBIS system. Early use of the rIBIS system by a software system design team suggests that users' acceptance increases as they continue to use the tool. We conclude that rIBIS effectiveness is affected by both people and implementation issues.     

用户界面设计中任务建模方法研究

基于模型的用户界面设计方法是通过用户界面模型开发用户界面的新方法。任务模型作为其中一个主要模型,刻画的是用户与界面交互过程中动态行为方面的信息。详细介绍了HTA,UAN,GOMS,CTT,Wisdom五种常用的任务模型建模方法,分析了各方法的优缺点及适用环境,并对任务建模方法的未来发展方向进行了展望。     

Participatory knowledge-management design: A semiotic approach

The aim of this paper is to present a design strategy for collaborative knowledge-management systems based on a semiotic approach. The contents and structure of experts' knowledge is highly dependent on professional or individual practice. Knowledge-management systems that support cooperation between experts from different (sub-)fields need to be situated and tailored to provide effective support even if the common aspects of the data need to be described by ontologies that are generic in respect to the sub-disciplines involved. To understand and approach this design problem, we apply a semiotic perspective to computer application and human–computer interaction. From a semiotic perspective, the computer application is both a message from the designer to the user about the structure of the problem domain, as well as about interaction with it, and a structured channel for the user's communication with herself, himself or other users of the software. Tailoring or “end-user development” – i.e. adapting the knowledge-management system to a specific (sub-)discipline, task or context – then refines both the message and adapts the structure of the interaction to the situated requirements.The essential idea of this paper is to define a new perspective for designing and developing interactive systems to support collaborative knowledge management. The key concept is to involve domain experts in participatory knowledge design for mapping and translating their professional models into the proper vocabularies, notations, and suitable visual structures for navigating among interface elements. To this end, the paper describes how our semiotic approach supports processes for representing, storing, accessing, and transferring knowledge through which the information architecture of an interactive system can be defined. Finally, the results of applying our approach to a real-world case in an archaeological context are presented.     

一种空间上下文感知的提及目标推荐方法

作为一种新兴的社交媒体用户交互服务,提及机制(mention mechanism)正在用户在线交互和网络信息传播方面扮演着重要角色.对用户提及行为的研究能够揭示用户的隐式偏好与其显式行为之间的联系,为信息传播监控、商业智能、个性化推荐等应用提供新的数据支撑.当前,对用户提及机制的探索多集中在其信息传播属性上,缺少从普通用户角度对其用户交互属性的学习.通过对普通用户提及行为的分析和建模构建一个推荐系统,为给定的社交媒体消息生成目标用户推荐.通过对大型真实社交媒体数据集的分析发现,用户的提及行为受其提及活动的语义和空间上下文因素的联合影响.据此,提出一个联合概率生成模型JUMBM(joint user mention behavior model),模拟用户空间关联提及活动的生成过程.通过对用户语义和空间上下文感知的提及行为进行统一建模,JUMBM能够同时发掘用户的移动模式、地理区域依赖的语义兴趣及其对应目标用户的地理聚集模式.此外,提出一种混合剪枝算法,加快推荐系统对在线top-k查询的响应速度.在大型真实数据集上的实验结果表明,所提方法在推荐有效性和推荐效率方面均优于对比方法.     

Understanding User Experience with Computer-Based Applications with Different Use Purposes

The concept of user experience emphasizes the importance of understanding users for applications that have various contextual features. To address this issue, this study examines the changes in the relationships among user satisfaction and users' perceptions of usability and aesthetics according to use situations. For data, an experiment was conducted using 15 existing websites with similar levels of usability and aesthetics. Forty-five engineering students participated in the experiment. The results indicated that the relationships among perceived usability, perceived aesthetics, and user satisfaction could be dependent on how users perceived the use purposes and interaction types of the websites. Specifically, the relationship between perceived usability and user satisfaction was stronger for websites requiring users' goal-directed activities, whereas the relationship between perceived aesthetics and user satisfaction was stronger for the websites mainly providing useful information, regardless of the existence of a specific use goal. Also, the strong relationship between perceived usability and perceived aesthetics was more obvious for websites where users mainly wanted to obtain information than for those where users primarily wanted to use the leisure and relaxation content. The findings can be utilized in the design of websites with different contextual features, especially related to use purposes and interaction types.     

Collaborative video searching on a tabletop

Almost all system and application design for multimedia systems is based around a single user working in isolation to perform some task yet much of the work for which we use computers to help us, is based on working collaboratively with colleagues. Groupware systems do support user collaboration but typically this is supported through software and users still physically work independently. Tabletop systems, such as the DiamondTouch from MERL, are interface devices which support direct user collaboration on a tabletop. When a tabletop is used as the interface for a multimedia system, such as a video search system, then this kind of direct collaboration raises many questions for system design. In this paper we present a tabletop system for supporting a pair of users in a video search task and we evaluate the system not only in terms of search performance but also in terms of user–user interaction and how different user personalities within each pair of searchers impacts search performance and user interaction. Incorporating the user into the system evaluation as we have done here reveals several interesting results and has important ramifications for the design of a multimedia search system.     

The effects of prototype medium on usability testing

Inconsistencies among testing methods and results in previous research prompted this study that builds upon a systematic usability testing research framework to better understand how interface medium influences users' abilities to detect usability flaws in applications. Interface medium was tested to identify its effects on users' perceptions of usability and abilities to detect usability problems and severe usability problems. Results indicated that medium has no effect on users' abilities to detect usability problems or perceptions of usability. However, results did indicate an interaction between the medium and the tested application in which users were able to identify significantly more usability problems on a higher fidelity medium using a particular application. Results also indicated that as users' perceptions of an application's usability increases, the users are less able to detect usability problems in that application. Usability testing should begin early in the design process, even if low fidelity mediums will be used.     

Needs identification methodology for inclusive design

Identification of user needs is an essential phase in the early stages of every design project. Many needs identification methodologies are described in the literature. When targeting users with special needs, the task becomes more challenging for different reasons (difficulty of retrieving information, performing prototype testing, etc.). This article presents a novel methodology, Needs Identification Methodology for Inclusive Design (NIMID), that guides the process of needs identification in the inclusive design scenario considering users’ physical, sensorial and cognitive capabilities. NIMID is grounded in Abowd and Beale's human–computer interaction framework and uses WHO's International Classification of Functionalities as the taxonomy that provides a common language. We exemplify the application of the methodology in the design of a smart oven for elderly people. We also compare NIMID with other methodologies evidencing its strong points: universality (common international classification of functioning language), systematicity (clearly defined phases and outcomes) and rationality (grounded in well-established interaction theory).