Predicting user personality by mining social interactions in Facebook

Adaptive applications may benefit from having models of users? personality to adapt their behavior accordingly. There is a wide variety of domains in which this can be useful, i.e., assistive technologies, e-learning, e-commerce, health care or recommender systems, among others. The most commonly used procedure to obtain the user personality consists of asking the user to fill in questionnaires. However, on one hand, it would be desirable to obtain the user personality as unobtrusively as possible, yet without compromising the reliability of the model built. On the other hand, our hypothesis is that users with similar personality are expected to show common behavioral patterns when interacting through virtual social networks, and that these patterns can be mined in order to predict the tendency of a user personality. With the goal of inferring personality from the analysis of user interactions within social networks, we have developed TP2010, a Facebook application. It has been used to collect information about the personality traits of more than 20,000 users, along with their interactions within Facebook. Based on all the collected data, automatic classifiers were trained by using different machine-learning techniques, with the purpose of looking for interaction patterns that provide information about the users? personality traits. These classifiers are able to predict user personality starting from parameters related to user interactions, such as the number of friends or the number of wall posts. The results show that the classifiers have a high level of accuracy, making the proposed approach a reliable method for predicting the user personality     

一个智能用户接口Agent设计与实现

文章主要介绍了DOLTRI-Agent(distance and open learning training resource information retrieval agent)系统中的用户接口Agent(NanDa user interface agent, 简称NDUIA)的设计和实现的关键技术.此系统扩展了memory-based reasoning技术,采用了多个记忆模型和多个分析模型,通过对不同用户使用经验的分析产生该用户专用的用户兴趣模型;同时根据用户兴趣模型和特定场景的使用经验共同作用来提供主动的智能服务,包括信息导引、搜索结果的预处理、智能即时帮助和分类信息的修改等,从而实现软件与人的协作.     

Human interaction with IoT-based smart environments

This paper describes concepts, design, implementation, and performance evaluation of a 3D-based user interface for accessing IoT-based Smart Environments (IoT-SE). The generic interaction model of the described work addresses some major challenges of Human-IoT-SE-Interaction such as cognitive overload associated with manual device selection in complex IoT-SE, loss of user control, missing system image or over-automation. To address these challenges we propose a 3D-based mobile interface for mixed-initiative interaction in IoT-SE. The 3D visualization and 3D UI, acting as the central feature of the system, create a logical link between physical devices and their virtual representation on the end user’s mobile devices. By so doing, the user can easily identify a device within the environment based on its position, orientation, and form, and access the identified devices through the 3D interface for direct manipulation within the scene. This overcomes the problem of manual device selection. In addition, the 3D visualization provides a system image for the IoT-SE, which supports users in understanding the ambience and things going on in it. Furthermore, the mobile interface allows users to control the amount and the way the IoT-SE automates the environment. For example, users can stop or postpone system triggered automatic actions, if they don’t like or want them. Users also can remove a rule forever. By so doing, users can delete smart behaviors of their IoT-SE. This helps to overcome the automation challenges. In this paper, we present the design, implementation and evaluation of the proposed interaction system. We chose smart meeting rooms as the context for prototyping and evaluating our interaction concepts. However, the presented concepts and methods are generic and could be adapted to similar environments such as smart homes. We conducted a subjective usability evaluation (ISO-Norm 9241/110) with 16 users. All in one the study results indicate that the proposed 3D-User Interface achieved a good high score according to the ISO-Norm scores.     

Adaptation in virtual environments: conceptual framework and user models

When interacting in a virtual environment, users are confronted with a number of interaction techniques. These interaction techniques may complement each other, but in some circumstances can be used interchangeably. Because of this situation, it is difficult for the user to determine which interaction technique to use. Furthermore, the use of multimodal feedback, such as haptics and sound, has proven beneficial for some, but not all, users. This complicates the development of such a virtual environment, as designers are not sure about the implications of the addition of interaction techniques and multimodal feedback. A promising approach for solving this problem lies in the use of adaptation and personalization. By incorporating knowledge of a user’s preferences and habits, the user interface should adapt to the current context of use. This could mean that only a subset of all possible interaction techniques is presented to the user. Alternatively, the interaction techniques themselves could be adapted, e.g. by changing the sensitivity or the nature of the feedback. In this paper, we propose a conceptual framework for realizing adaptive personalized interaction in virtual environments. We also discuss how to establish, verify and apply a user model, which forms the first and important step in implementing the proposed conceptual framework. This study results in general and individual user models, which are then verified to benefit users interacting in virtual environments. Furthermore, we conduct an investigation to examine how users react to a specific type of adaptation in virtual environments (i.e. switching between interaction techniques). When an adaptation is integrated in a virtual environment, users positively respond to this adaptation as their performance significantly improve and their level of frustration decrease.     

Analyzing the Uses of a Software Modeling Tool

While a lot of progress has been made in improving analyses and tools that aid software development, less effort has been spent on studying how such tools are commonly used in practice. A study into a tool's usage is important not only because it can help improve the tool's usability but also because it can help improve the tool's underlying analysis technology in a common usage scenario. This paper presents a study that explores how (beginner) users work with the Alloy Analyzer, a tool for automatic analysis of software models written in Alloy, a first-order, declarative language. Alloy has been successfully used in research and teaching for several years, but there has been no study of how users interact with the analyzer. We have modified the analyzer to log (some of) its interactions with the user. Using this modified analyzer, 11 students in two graduate classes formulated their Alloy models to solve a problem set (involving two problems, each with one model). Our analysis of the resulting logs (total of 68 analyzer sessions) shows several interesting observations; based on them, we propose how to improve the analyzer, both the performance of analyses and the user interaction. Specifically, we show that: (i) users often perform consecutive analyses with slightly different models, and thus incremental analysis can speed up the interaction; (ii) users' interaction with the analyzer is sometimes predictable, and akin to continuous compilation, the analyzer can precompute the result of a future action while the user is editing the model; and (iii) (beginner) users can naturally develop semantically equivalent models that have significantly different analysis time, so it is useful to study manual and automatic model transformations that can improve performance.     

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.     

个体交互行为的平滑干预模型

基于交互行为的用户特征提取和身份认证方法是一种重要的身份识别方式,但高频用户的交互行为模式和操作习惯相对稳定,易被欺诈者模仿,使得现有模型对此类欺诈行为的误判较高.如何使得用户行为主动平滑变化且可区分,成为解决上述问题的关键.针对此问题,提出一种基于个体交互行为系统平滑干预模型:首先,根据用户历史交互行为日志从多个维度...     

Value and relation display: interactive visual exploration of large data sets with hundreds of dimensions

Few existing visualization systems can handle large data sets with hundreds of dimensions, since high-dimensional data sets cause clutter on the display and large response time in interactive exploration. In this paper, we present a significantly improved multidimensional visualization approach named Value and Relation (VaR) display that allows users to effectively and efficiently explore large data sets with several hundred dimensions. In the VaR display, data values and dimension relationships are explicitly visualized in the same display by using dimension glyphs to explicitly represent values in dimensions and glyph layout to explicitly convey dimension relationships. In particular, pixel-oriented techniques and density-based scatterplots are used to create dimension glyphs to convey values. Multidimensional scaling, Jigsaw map hierarchy visualization techniques, and an animation metaphor named Rainfall are used to convey relationships among dimensions. A rich set of interaction tools has been provided to allow users to interactively detect patterns of interest in the VaR display. A prototype of the VaR display has been fully implemented. The case studies presented in this paper show how the prototype supports interactive exploration of data sets of several hundred dimensions. A user study evaluating the prototype is also reported in this paper     

Dynamic adaptation of numerical attributes in a user profile

Recommender systems try to help users in their decisions by analyzing and ranking the available alternatives according to their preferences and interests, modeled in user profiles. The discovery and dynamic update of the users’ preferences are key issues in the development of these systems. In this work we propose to use the information provided by a user during his/her interaction with a recommender system to infer his/her preferences over the criteria used to define the decision alternatives. More specifically, this paper pays special attention on how to learn the user’s preferred value in the case of numerical attributes. A methodology to adapt the user profile in a dynamic and automatic way is presented. The adaptations in the profile are performed after each interaction of the user with the system and/or after the system has gathered enough information from several user selections. We have developed a framework for the automatic evaluation of the performance of the adaptation algorithm that permits to analyze the influence of different parameters. The obtained results show that the adaptation algorithm is able to learn a very accurate model of the user preferences after a certain amount of interactions with him/her, even if the preferences change dynamically over time.     

Optimal Design of Object-Oriented Databases in Automatic Information-Control Systems. I. Analysis of Problem Domains

Design of object-oriented databases for automatic information control systems is studied. A formal method of analysis and design of optimal structures for object-oriented databases is developed on the basis of sequential interconnected formalizations of user problem domains, clustering of user information and functional requirements, design and analysis of object models for user requirements and object canonical structure of databases and design of optimal logical structures for object-oriented databases. Methods of analysis of problem domains of database users and construction of effective object canonical database structures in the form of classes, objects, and their relations and satisfying principles of abstraction, encapsulation, modularity, and hierarchy are described.     

基于卷积神经网络交互的用户属性偏好建模的推荐模型

潜在因子模型（LFM）以其优异的性能在推荐领域得到了广泛应用。在LFM中除了使用交互数据以外,辅助信息也被引入用于解决数据稀疏的问题,从而提升推荐的性能。然而,大多数LFM仍然存在一些问题：第一,LFM在对用户进行建模时,忽略了用户如何根据其特征偏好对项目作出决策;第二,采用内积的特征交互假设特征维度之间是相互独立的,而没有考虑到特征维度之间的关联。针对上述问题,提出一种新的推荐模型：基于卷积神经网络（CNN）交互的用户属性偏好建模的推荐模型（UAMC）。该模型首先获得用户的一般偏好、用户属性和项目嵌入,然后将用户属性和项目嵌入进行交互,以探索用户不同的属性对不同项目的偏好;接着将交互过的用户偏好属性送入CNN层来探索不同偏好属性的不同维度的关联,从而得到用户的属性偏好向量;接着使用注意力机制结合用户的一般偏好和CNN层得到的属性偏好,从而获得用户的向量表示;最后采用点积来计算用户对项目的评分。在Movielens-100K、Movielens-1M和Book-crossing这三个真实的数据集上进行了实验。实验结果表明,所提模型在均方根误差（RMSE）上与稀疏数据预测的神经网络分解机（NFM）模型相比分别降低了1.75%、2.78%和0.25%,验证了在LFM的评分预测推荐中,UAMC在提升推荐精度上的有效性。     

ON-LINE AUTOMATIC HELP GENERATION SYSTEMS

The design of good user interfaces enhances the acceptance and use of computers, basically in environments in which their users are not familiar with computers. In this paper we concentrate on the design and development of intelligent interaction systems that provide active context-sensitive assistance to the user. We seek a compromise solution between development simplicity and power. To reach this objective, we propose the application of techniques from knowledge engineering to the development of active on-line assistance systems, establishing total independence between the knowledge on the interaction domain, the data, and the control of the communication acts.     

数据驱动的移动应用用户接受度建模与预测

应用市场（app market）已经成为互联网环境下软件应用开发和交付的一种主流模式.相对于传统模式,应用市场模式下,软件的交付周期更短,用户的反馈更快,最终用户和开发者之间的联系更加紧密和直接.为应对激烈的竞争和动态演变的用户需求,移动应用开发者必须以快速迭代的方式不断更新应用,修复错误缺陷,完善应用质量,提升用户体验.因此,如何正确和综合理解用户对软件的接受程度（简称用户接受度）,是应用市场模式下软件开发需考量的重要因素.近年来兴起的软件解析学（software analytics）关注大数据分析技术在软件行业中的具体应用,对软件生命周期中大规模、多种类的相关数据进行挖掘和分析,被认为是帮助开发者提取有效信息、作出正确决策的有效途径.从软件解析学的角度,首先论证了为移动应用构建综合的用户接受度指标模型的必要性和可行性,并从用户评价数据、操作数据、交互行为数据这3个维度给出基本的用户接受度指标.在此基础上,使用大规模真实数据集,在目标用户群体预测、用户规模预测和更新效果预测等典型的用户接受度指标预测问题中,结合具体指标,提取移动应用生命周期不同阶段的重要特征,以协同过滤、回归融合、概率模型等方法验证用户接受度的可预测性,并讨论了预测结果与特征在移动应用开发过程中可能提供的指导.     

User viewpoint modelling: understanding and representing user viewpoints during requirements definition

There has been increasing awareness of the impact of the early stages of systems development on the quality of information systems. A critical early activity is requirements definition, when the requirements for an information system are determined. Traditional requirements capture techniques do not support the collaborative nature of requirements definition or the emergent nature of requirements themselves. This paper focuses on viewpoint development as a means of resolving some of the difficulties of requirements definition. It proposes a user viewpoint model for capturing and representing the viewpoints of users during requirements acquisition. The model can facilitate communication and interaction between analysts and users and help build a shared understanding of requirements. It can be used to structure the requirements acquisition process. The model provides for evaluation of requirements acquisition techniques to guide the selection of appropriate techniques for developing user viewpoint models. The paper reports a multiple-case study of requirements definition efforts that examined user viewpoint development in practice and used the cases to validate empirically the concepts of the user viewpoint model. The implications of the case study findings for requirements definition practice are discussed, and some areas for future research are identified.     

Texture Inpainting for Photogrammetric Models

We devise a technique designed to remove the texturing artefacts that are typical of 3D models representing real-world objects, acquired by photogrammetric techniques. Our technique leverages the recent advancements in inpainting of natural colour images, adapting them to the specific context. A neural network, modified and trained for our purposes, replaces the texture areas containing the defects, substituting them with new plausible patches of texels, reconstructed from the surrounding surface texture. We train and apply the network model on locally reparametrized texture patches, so to provide an input that simplifies the learning process, because it avoids any texture seams, unused texture areas, background, depth jumps and so on. We automatically extract appropriate training data from real-world datasets. We show two applications of the resulting method: one, as a fully automatic tool, addressing all problems that can be detected by analysing the UV-map of the input model; and another, as an interactive semi-automatic tool, presented to the user as a 3D ‘fixing’ brush that has the effect of removing artefacts from any zone the users paints on. We demonstrate our method on a variety of real-world inputs and provide a reference usable implementation.     

Characterising user capabilities to support inclusive design evaluation

Designers require knowledge and data about users to effectively evaluate product accessibility during the early stages of design. This paper addresses this problem by setting out the sensory, cognitive and motor dimensions of user capability that are important for product interaction. The relationship between user capability and product demand is used as the underlying conceptual model for product design evaluations and for estimating the number of people potentially excluded from using a given product.     

应用B样条活动曲线模型实现超声图像的分割

声图像由于质量较差无法实现全自动的分割方法.提出了一个新的超声图像的半自动分割方法.该方法把用户交互作为一个重要因素结合到传统的B样条活动曲线模型中.这种半自动的分割方法仅需少量的用户交互,特点是:通过用户交互,规范B样条活动曲线模型,约束曲线的活动形状和范围;引入新的规则使B样条活动曲线迅速移动到用户指定的正确边界处;并且通过观察被用户接受的边界实时地训练模型.该方法是一个快速、有效的超声图像分割方法,尤其适用于连续多个相关超声图像的处理,现已成功地运用到肝肿瘤手术仿真系统当中.     

From user interface design to the support of intelligent and adaptive interfaces: an overhaul of user interface software infrastracture

Research on adaptive interfaces in the past has lacked support from user interface tools which allow interfaces to be easily created and modified. Also, current user interface tools provide no support for user models which can collect task-oriented information about users. Developing an adaptive interface requires a user model and an adaptation strategy. It also, however, requires a user interface which can be adapted. The latter task is often time-consuming, especially in relation to more sophisticated user interfaces.

The paper presents a user interface design environment, UIDE, which has a different software infrastracture. Designers use high-level specifications to create a model of an application and links from the application to various interface components. The model is the heart of all the design and run-time support in UIDE, including automatic dialog sequencing and help generation. UIDE provides automatic support for collecting task-oriented information about users, by the use of its high-level specifications in its application model as a basic construct for a user model. Some examples of adaptive interfaces and adaptive help are presented that use the information that is collectable in UIDE.     

基于多维度兴趣注意力和用户长短期偏好的新闻推荐

在这个网络媒体平台成为获取新闻资讯的主流方式的时代,新闻推荐扮演着至关重要的角色。一方面,媒体平台使用新闻推荐可帮助用户过滤掉不感兴趣的新闻,定制个性化阅读内容推送;另一方面,智能推送服务能够增加新闻点击率,帮助媒体平台实现新闻的快速传播。目前,新闻推荐逐渐成为数据分发领域核心技术之一,逐渐引起国内外学者的关注。该文针对新闻热度不均衡问题造成的长尾现象,提出了一种基于多维度兴趣注意力的用户长短期偏好的新闻推荐模型。首先,对用户长期偏好进行挖掘时把用户兴趣分成多个维度,并采用注意力机制控制不同兴趣维度的重要程度,从而学习到包含不同维度兴趣信息的长期偏好。其次,采用CNN与注意力网络相结合的模型对新闻进行表示学习,采用GRU在用户近段时间内的阅读历史中学习用户短期偏好。最后,通过大量在真实新闻数据集上的实验,以AUC、MRR、NDCG为评价指标与其他基线方法进行比较,证实了该模型均优于其他方法。     

The effect of a database feedback system on user performance

There are two main approaches to improving the effectiveness of database interfaces. One is to raise the level of abstraction for the content of the user-database interaction. The relational model belonging to the logical level has replaced the hierarchical and network models that belong to the lower physical level. It is likely that the relational model will eventually be replaced by models belonging to the even higher conceptual level, such as entity relationship models and object-oriented models. The second approach is to enhance the actual interaction process. This can be done by providing better feedback to the user. Feedback can be in the form of more comprehensible error messages, and the provision of a natural language interpretation of user's query. Such a feedback system was developed, and its effectiveness tested in an experiment. The results showed that the feedback system enhanced user performance greatly. Specifically, users who used the feedback system were 12.9% more accurate than those without the feedback system. They were also 41.2% more confident of their answers, and they took 29.0% less time than those without the feedback system.