Task-based method for creating usable hypertext

Although large hypertext documentation systems have many benefits in the commercial world, they can be difficult to build and use. To help overcome both these obstacles, a method under development at Hewlett-Packard assists authors in creating usable hypertext. A Wizard of Oz experiment was done with traditional on-line documentation and hypertext documentation to see what users liked and disliked. The experiment showed the need for a set of hypertext construction rules to ensure usability. Following these rules, and with computer assistance, authors are expected to do a task analysis of users' activities, to identify critical objects and create content nodes for them, to create links between nodes within clearly defined and cognitively justified limits, and to conduct usability tests on the resulting hypertext volume. Whilst this method recognises the importance of good clear writing, the rules and suggested prectices are not primarily about writing or screen design, but about creating a coherent navigational web that ensures success among commercial users of hypertext. The authoring system described in this paper has been developed for the HP Help system, which has been adopted as the common help delivery system for developers of Common Open Systems Environments on Unix-like platforms.     

The potential for social contextual and group biases in team decision-making: biases,conditions and psychological mechanisms

Abstract

Users' mental models of systems are frequently asserted to be important in their interactions with those systems. Although there are few explicit definitions of mental models in the literature, mental models are assumed to be important and researchers have seemed to accept and understand the concept intuitively. In our research, we have extracted three themes from the definitions of mental models including: (1) the relations among features or components of a system; (2) the capability of the mental model to aid in the control of the system; and (3) the capability of the mental model to enhance the user's understanding of the system. The relationships among the components of users' mental models, including procedural and declarative knowledge, perceptions of the use of system features, and the relations among the similarity of use of system features, were investigated in a field study. Trained and untrained novice users of a new business phone system rated the similarity of use of nine standard features on the phone. These ratings were used to derive cognitive representations of the relations among the system features. Users' ratings of features on univariate scales about the use of the features and scores obtained on a test of procedural knowledge were related to these representations. The two novice groups' mental models were similar except for the perception of one feature; it was more accurately depicted in the trained users' representation than those who did not attend a training programme. Two types of experts' similarity of use ratings were evaluated to determine an ‘appropriate’ representation of the use of the system features; this was then compared to the novices'. This comparison suggested that there were deficiencies in the mental models of novices. Designing training programmes and instructional aids for systems using the discrepancies between novices' and experts' mental models are discussed.     

Knowledge acquisition using hypertext

This paper addresses the issue of supporting knowledge acquisition using hypertext. We propose a way of tightly integrating hypertext and structured object representation, using Artificial Intelligence (AI) frames for the basic representation of hypertext nodes. Epistemologically, a dual view of the resulting space is of interest. One view is that of hypertext which emphasizes nodes containg g text, including formal knowledge representation. The other view focuses on objects with certain relationships, which define a semantic network. Both in hypertext and in semantic networks the relations between chunks of knowledge are explicitly represented by links. However, in today's hypertext systems a node typically contains just informal text and references to other nodes. Our approach additionally facilitates the explicit representation of structure “inside” hypertext nodes using partitions. We show the usefulness of such a tight integration for knowledge acquisition, providing several features useful for supporting it based on a level of basic hypertext functionality. In particular, we sketch a method for doing knowledge acquisition in such an environment. Hypertext is used as a mediating “semiformal” representation, which allows experts to directly represent knowledge without the immediate support of knowledge engineers. These help then to make this knowledge operational, supported by the system's facility to provide templates as well as their links to the semiformal representation. As an example of our results of using this method of knowledge acquisition, we illustrate the strategic knowledge in our application domain. More generally, our approach supports important aspects of (software) engineering knowledge-based systems and their maintenance. Also their user interface can be improved this way.     

Automatic generation and refinement of hypertext links

Abstract

Current generation of hypertext systems suffer from the limitations that they are static in nature, and they do not support the automated process of link creation very well. Because of the efforts involved in manually creating links, the hyperbases created using these systems are seldom modified even when they were found not to fully support the requirements of the intended users. This paper studies the development of automated tools to aid in the process of link creation, browsing, and link refinement. Only relation links are considered in this study. The automated tools are developed to help in three of the major stages of developing and using hypertext applications: (a) during authoring to generate a set of relation links between pairs of nodes; (b) during browsing to recommend an optimal set of starting nodes for the users to begin browsing, and to guide the users at each stage of browsing by suggesting a set of “next” nodes to traverse; and, (c) during training to modify, remove and add links based on users' feedback data collected. The training will result in long-term changes in the hypertext structure.

In order to test the effectiveness of the training process objectively, a navigator is built to simulate the browsing activities of the users. The effects of training have been evaluated on two text collections using a variety of objective measures. The results indicate that the training process has improved the effectiveness of the hyperbase to support browsing.     

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。     

Iterative Visual Clustering for Learning Concepts from Unstructured Text

Discovering concepts from vast amount of text is is an important but hard explorative task. A common approach is to identify meaningful keyword clusters with interesting temporal distributive trends from unstructured text. However, usually lacking clearly de ned objective functions, users'' domain knowledge and interactions need to be feed back and to drive the clustering process. Therefore we propose the iterative visual clustering (IVC), a noval visual text analytical model. It uses di erent types of visualizations to help users cluster keywords interactively, as well as uses graphics to suggest good clustering options. The most distinctive di erence between IVC and traditional text analytical tools is, IVC has a formal on-line learning model which learns users'' preference iteratively: during iterations, IVC transforms users'' interactions into model training input, and then visualizes the output for more users interactions. We apply IVC as a visual text mining framework to extract concepts from nursing narratives. With the engagement of domain knowledge, IVC has achieved insightful concepts with interesting patterns.     

Do we trust the crowd or information system? Effects of personalization and bandwagon cues on users' attitudes and behavioral intentions toward a restaurant recommendation website

Visual interface cues on many websites can influence Internet users' psychology, especially their perceptions about the site as well as its content (Sundar, 2008). Specifically, presence of commonly used interface cues (e.g., personalization, bandwagon cues) can substantially influence users' attitudes and their behavioral intentions toward websites and their content. This study examined the effect of personalization feature and bandwagon cues (i.e., star ratings, reviews) in a restaurant recommendation website, measuring (a) to what extent users positively perceive and plan on revisiting or sharing the site, and (b) to what degree users favored the recommended restaurant and plan to visit them. A 2 (personalization feature: present vs. absent) × 2 (bandwagon cues: high vs. low) between-subjects experiment showed that personalization feature and bandwagon cues increased positive perceptions and their behavioral intentions toward both the website and the recommended restaurant. Moreover, results revealed that users' perceived relevance as well as perceived novelty mediated the effects of interface cues on their attitudinal and behavioral consequences. Further, the impact of the interface cues on user psychology significantly differed as a function of the other cues. Theoretical and practical implications for future research on the effect of interface cues on user psychology are discussed.     

On keys' meanings and modes: the impact of different key solutions on children's efficiency using a mobile phone

The present study investigates the impact of different key solutions of mobile phones on users' effectiveness and efficiency using the devices. In the first experiment, 36 children (9 – 14 years) and in the second experiment 45 young adults (19 – 33 years) completed four common phone tasks twice consecutively on three simulated phones that had identical menus, but different key solutions. An approach was undertaken to quantify the complexity of keys in three models, incorporating different factors contributing to the keys' complexity (number of key options, number of modes and number of modes with a semantically dissimilar meaning), in order to predict users' performance decrements. As a further main factor, the degree of the users' locus of control (LOC) was measured and interactions with performance outcomes were studied. As dependent measures, the number of inefficient keystrokes, the number of tasks solved and the processing time were determined. Results showed a significant effect of control key solutions on users' efficiency and effectiveness for both children and young adults. Moreover, children's LOC values significantly interacted with performance: children with low LOC values showed the lowest performance and no learnability, especially when using keys with a high complexity. From the three factors contributing to the complexity of keys, keys exerting different functions with semantically inconsistent meanings had the worst effect on performance. It is concluded that in mobile user interface design keys with semantically inconsistent meanings should be generally avoided.     

The Rhetoric of Hypertext

This study adopts as a fundamental orientation the view that hypertext may eventually bring about a paradigm shift in text delivery and in human information processing. However, paradigm shifts do not occur overnight; they are evolutionary rather than revolutionary. Because of the considerable commitment of Western knowledge and culture to the written word and to linear text, it seems likely that successful hypertext systems will — at least in the beginning — electronically emulate many of the strategies a sophisticated reader uses in dealing with hard copy. This article describes a project which modeled the functionality an intelligent reader would bring to paper text (specifically, a maintenance manual), and designed and implemented a hypertext version of the document using Apple Computer's HyperCard.

Since few fully specified hypertext systems have been deployed, the research described here was undertaken to build a platform on which notions about the efficacy of non-linear text processing for a specific application could be tried out. This article describes a Stackware version of a portion of an aircraft maintenance manual and considers issues of (1) data storage models, (2) user interface, and (3) information retrieval methods for online text. These elements — among others — are the essence of the new rhetoric for non-sequential text.     

Comprehension and navigation of networked hypertexts

This study aims to investigate secondary school students' reading comprehension and navigation of networked hypertexts with and without a graphic overview compared to linear digital texts. Additionally, it was studied whether prior knowledge, vocabulary, verbal, and visual working memory moderated the relation between text design and comprehension. Therefore, 80 first‐year secondary school students read both a linear text and a networked hypertext with and without a graphical overview. Logfiles registered their navigation. After reading the text, students answered textbased multiple choice questions and drew mindmaps to assess their structural knowledge of each text content. It was found that both textbased and structural knowledge were lower after reading a networked hypertext than a linear text, especially in students with lower levels of vocabulary. Students took generally more time to read the hypertext than the linear text. We concluded that networked hypertexts are more challenging to read than linear texts and that students may benefit from explicit training on how to read hypertexts.     

Semantic similarity based approach for reducing Arabic texts dimensionality

An efficient method is introduced to represent large Arabic texts in comparatively smaller size without losing significant information. The proposed method uses the distributional semantics to build the word-context matrix representing the distribution of words across contexts and to transform the text into a vector space model (VSM) representation based on word semantic similarity. The linguistic features of the Arabic language, in addition to the semantic information extracted from different lexical-semantic resources such as Arabic WordNet and named entities’ gazetteers are used to improve the text representation and to create word clusters of similar and related words. Distributional similarity measures have been used to capture the words’ semantic similarity and to create clusters of similar words. The conducted experiments have shown that the proposed method significantly reduces the size of text representation by about 27 % compared with the stem-based VSM and by about 50 % compared with the traditional bag-of-words model. Their results have shown that the amount of dimension reduction depends on the size and shape of the windows of analysis as well as on the content of the text.     

Heart period variability as mental effort monitor in Human Computer Interaction

Elementary steps of H uman Computer Interaction (HCI), like users' mental actions followed by a series of keystrokes and mouse-clicks, are the basic components of using information technological systems. This is why examination methods capable of assessing users' actual mental effort corresponding to these elementary steps during HCI in a scientifically sound way have great importance. It is known that under certain circumstances, Heart Period Variability (HPV) could be a measure of actual mental effort. This paper gives a short overview of applications of HPV in ergonomics in general and, based on empirical evidence intends to prove that this methodology, after a careful adaptation, could be powerful technique for monitoring mental effort in HCI. The paper outlines the main components of the INTERFACE testing workstation and the related methodology for investigatingamong others-users mental effort. A detailed application example is also provided.     

The Role of Structure and Content in Perception of Visual Similarity Between Web Pages

In human–computer interaction, users' perception of visual similarity in interfaces may affect how well they judge the relevance of information, construct appropriate mental models, and effectively interact with computers. This is of interest to both computer science and psychology. A review of the theoretical and applied research in visual similarity reveals both a content-oriented and a structural-oriented approach. The present study seeks to understand the content and structural aspects of visual similarity judgment. Unlike early theoretical studies in psychology, web pages were used as realistic stimulus in an experimental study. Structural and content changes to pairs of web pages were incrementally applied in experimental sessions while participants were judging the similarity of these pairs. The results of the experiment indicated that similarity ratings between two pages correlate negatively with the number of alterations made to the layout of one of the pages. Similarity ratings between two pages also declined when distinctive background colors were applied to one of the pages. The experiment also revealed that text-complete web pages received lower similarity ratings than wire frames of the pages. Pages with readable text received higher similarity ratings than pages with unreadable text. The results of this study will help web designers produce web pages of various similarities that will be consistent with users' judgment and help improve similarity-based web researches.     

融合多模态自监督图学习的视频推荐模型

现有视频推荐方法在算法框架中引入图神经网络来建模用户—视频协同关系,学习用户和视频的表示向量,但是节点中包含的冗余噪声会限制模型的建模能力。针对以上问题,提出了一种融合多模态自监督图学习的视频推荐模型(IMSGL-VRM)。首先,在图数据增强模式下构建自监督的图神经网络模型学习多模态视图下的节点特征表示,以提升节点表示的泛化能力;其次,为了得到推荐结果的多样性,设计了多兴趣提取模块从用户历史的交互视频序列中建模用户的多兴趣;最后,融合多模态的用户多兴趣表示和视频的特征表示,使用多样性可控的方式输出推荐结果,以满足视频推荐的多样性需求。在MovieLens-1M和TikTok数据集上实验,采用准确性、召回率、NDCG和多样性等指标评估模型。实验结果表明,该模型相比经典基准模型均有显著的性能提升。     

The relative effectiveness of hypertext and text

A series of two experiments was conducted. In Experiment 1, participant performance when using a hypertext electronic reference system was compared to using a conventional reference book. The links in this hypertext were based on the index entries in the corresponding 529‐page book. Specific topics and particular facts were located much faster and more accurately using the hypertext system than for the book. These advantages increased when participants searched for information that was either not included or referred to indirectly in the index. However, hypertext did not have an advantage over text on learning tasks. The conclusion was that hypertext is superior to text only for “reading‐to‐do” tasks similar to those a designer may perform when consulting a reference book. Experiment 2 compared user performance when the links corresponded exactly to the original index of a 545‐page textbook on ergonomics to performance when the links were generated by computer key‐word searches. Strong advantages were found in speed, accuracy, and subjective ratings for links based on the author's original index. It appears that these latter results can be attributed to the greater focus of the information provided by links based on the author's index. Users spent much less time browsing irrelevant sections of the book.     

一种基于协同上下文关系学习的同城活动推荐算法

新兴的基于活动的社交网络以活动为核心,结合线上关系与线下活动促进用户真实、有效的社交关系的形成,但过多的活动信息会使用户难以分辨和选择.结合上下文进行个性化同城活动推荐,是解决活动信息过载问题的一种有效手段.然而大部分现有的同城活动推荐算法都是从用户参与活动记录中间接统计用户对上下文信息的偏好,忽略了两者之间潜在的交叉影响关系,从而影响了推荐结果的有效性.为了解决用户参与活动偏好与上下文信息潜在交叉影响关系利用不足的问题,提出了一种基于协同上下文关系学习的同城活动推荐算法（colletivecontextual relation learning,简称CCRL）.首先,对用户参与活动记录和活动主办方、活动内容、活动地点、举办时间等相关上下文信息进行关系建模;然后,采用多关系贝叶斯个性化排序学习方法进行协同上下文关系学习及同城活动推荐.Meetup数据集上的实验结果表明,该算法在多项指标上均优于现有的主流活动推荐算法.     

Evaluation of users' privacy concerns by checking of their WhatsApp status

WhatsApp Messenger is a popular instant messenger among Iranian users. The WhatsApp status feature provides the possibility of posting desired content without restrictions in terms of type with the capability of being managed by users. Status can be considered as a potential place to express users' feelings, opinions, and thoughts. However, special attention should be paid to the privacy of users and the information published in this manner because access to the content of a user's status by unauthorized friends and interpretations of the user's status content may violate his/her privacy. This study investigates the privacy issues associated with information shared through status. The data of this study were gathered via access to the status content of 4000 Iranian users and via telephone interviews conducted with 350 of them. In this study, a combination of quantitative and qualitative methods has been used to analyze the data. This study focuses on the extraction of patterns in users' status content, determination of their polarity, and examination of the factors affecting users' privacy concerns. During the research, 10 general themes were extracted from users' content. The results showed that user privacy concerns influenced the type of theme selected. In addition, the theme selected under different circumstances may include a type of feeling that, in this study, is called polarity. Polarity is affected by the users' privacy concerns. Moreover, the demographic characteristics of users (age and gender) have a significant relationship with the type of theme used and their privacy concerns.     

Confidentiality Protection in Cloud Computing Systems

Current cloud computing systems pose serious limitation to protecting users'' data confidentiality. Since users'' sensitive data is presented in unencrypted forms to remote machines owned and operated by third party service providers, the risks of unauthorized disclosure of the users'' sensitive data by service providers may be high. Many techniques for protecting users'' data from outside attackers are available, but currently there exists no effective way for protecting users'' sensitive data from service providers in cloud computing. In this paper, an approach is presented to protecting the confidentiality of users'' data from service providers, and ensures that service providers cannot access or disclose users'' confidential data being processed and stored in cloud computing systems. Our approach has three major aspects: 1) separating software service providers and infrastructure service providers in cloud computing, 2) hiding information of the owners of data, and 3) data obfuscation. An example to show how our approach can protect the confidentiality of users'' data from service providers in cloud computing is given. Experimental results are presented to show that our approach has reasonable performance.     

基于用户潜在兴趣的知识感知传播推荐算法

知识图谱引入推荐系统可以利用知识图谱实体之间的语义关系学习用户及项目表示。基于嵌入传播的方法利用知识图谱的图结构学习相关特征,但随着传播范围增加,多跳实体间的语义相关性减小。为有效提升推荐语义表达能力并提高推荐准确度,提出基于用户潜在兴趣的知识感知传播推荐模型,该模型采用异构传播方式传播项目关联知识并迭代学习用户的潜在兴趣,以此增强模型对用户与项目的表示能力。具体地,首先图嵌入层生成用户与项目的初始化表示,随后在异构传播层中采用知识感知注意力机制区分同一层中实体之间的重要性,更精确生成目标实体的表示。随后通过用户潜在兴趣传播学习用户的高阶潜在兴趣,增强多跳实体语义相关性。最后在预测层中使用信息衰减因子区分不同传播层次的重要性,生成用户及项目的最终表示。实验表明,该模型在Last. FM与Book-Crossing两个公开数据集上AUC值相较于最先进的基线提升了2.25%与4.71%,F1值分别提升3.05%和1.20%,recall@K值均优于对比的基线模型,提出的模型能有效提高推荐准确度。     

The segmented presentation of visually structured texts: Effects on text comprehension

The effects of a segmented presentation applied to a visually structured text were examined in the context of the explosion of small-screen devices. Empirical research investigating the influence of text signaling on text processing suggests that the text visual structure may influence comprehension by facilitating the construction of a coherent text representation. Undergraduate students were asked to read a text under different segmented conditions varying on the type of information provided about the text visual structure and on the segmentation unit. When the segmented presentation did not supply any information or when it only offered local information about the text visual structure, text comprehension depended on the segmentation unit. When the segmentation unit did not fit the text visual structure, an erroneous text representation was constructed, whereas the compatible segmentation unit led to a correct text comprehension. When the segmented presentation rendered the global text visual structure, the segmentation unit had no effect on comprehension and more readers constructed a correct and close text representation. Thus, the text visual structure seems to play a role in text comprehension and this role has to be taken into account for text segmented presentation.