基于知识图谱的智能问答意图识别联合模型

针对现有意图识别联合模型在专业领域知识图谱问答中容易发生识别领域实体以及问句分类错误的情况,提出一个结合了领域知识图谱的意图识别联合模型。该模型有三步,将领域知识图谱中实体对应的本体标签以及本体间关系导入训练数据集,形成包含本体标签的知识文本以及额外包含本体关系的知识文本图;通过字符级嵌入和位置信息嵌入将包含了本体标签的知识文本转化成嵌入表示并依据知识文本图创建实体关系可视矩阵,明确知识文本各成分的相关程度;将嵌入表示和实体关系可视矩阵输入模型编码层进行模型的训练。以高速列车领域知识图谱为例,经过准确率和召回率的验证,以该方法训练出的模型在高速列车领域问答数据集的意图识别任务上取得了更好的表现。     

食品包装材质对消费者绿色购买意愿影响的眼动研究

目的 探讨食品包装材质对消费者注意加工流程和绿色购买意愿影响的内在机制。方法 采用包装材质2(环保/普通)×食品类型2(实用品/享乐品)双因素实验设计,在货架购物场景下采用Tobii Glasses 2眼镜式眼动仪,采集被试者浏览货架不同食品时的眼动数据(平均注视时间、注视次数、热点图),并结合行为数据综合分析。结果 在平均注视时间上,包装材质与食品类型的交互作用显著,注视次数交互作用不显著;环保材质包装的食品获得更多关注,被试者偏好于选择环保包装的享乐食品。结论 包装材质与食品类型共同影响消费者的视觉感知效果与加工过程,环保包装对青年消费者的绿色购买意愿有正向促进作用。     

The impact of perceived risk,intangibility and consumer characteristics on online game playing

Online game is the most popular entertainment application in the virtual world and online gamers demonstrate high attachment to playing online games. Previous studies have linked to the numerous negative outcomes in playing online games. The factors contribute to the negative consequences on using online game have been relatively neglected. The purpose of this study is to explore the impact of perceived risk, intangibility, gender and age (adolescent/adult) difference on online game playing consequences and intentions. Past usage frequency is also made to look into the influence additional purchase intention. A total of 1418 useful questionnaires (including 1018 from public interview and 400 from online questionnaire feedback) were collected for final data analysis. The results demonstrated the important roles that time risk, psychological risk, financial risk, physical intangibility, mental intangibility and generality play on the negative consequences associated with online game playing. The results also indicated that male and adolescent individuals spent much more time on online game and intented to act the entertainment more than females and adults did. Finally, past online game playing frequency was showed to be a positive predictor of future online game playing intention.     

Exploring the value of purchasing online game items

The aims of this paper are to: (1) modify the theory of consumption values in order to investigate online game users’ perceived value of purchasable game items, and (2) develop a new construct – the “integrated value of purchasing game items” – based on the modified theory of consumption values. We found that the enjoyment, character competency, visual authority, and monetary values are appropriate for describing how online game users perceive the value of game items. Utilizing second order analysis, the “integrated value of purchasing game items” was developed. To show the validity of the new construct, we developed a research model and tested it using the results of 327 valid questionnaires. Results revealed that the new construct is statistically significant in affecting users’ intention to purchase game items.     

Using SERVQUAL to assess the quality of e-learning experience

Distance learning programs have been dramatically expanding in accordance with demand. Assessment of the quality of e-learning has become a strategic issue, one that is critical to program survival. In this study we propose a modified SERVQUAL instrument for assessing e-learning quality. The instrument consists of five dimensions: Assurance, Empathy, Responsiveness, Reliability, and Website Content. Data analysis from 203 e-learning students shows that four out of these five dimensions (except Reliability) play a significant role in perceived e-learning quality, which in turn affects learners’ satisfaction and future intentions to enroll in online courses. Managerial implications of the major findings are provided.     

Web-based Biometric Computer Mouse Advisory System to Analyze a User's Emotions and Work Productivity

This article describes the analysis of emotional state and work productivity using a Web-based Biometric Computer Mouse Advisory System to Analyze a User's Emotions and Work Productivity (Advisory system hereafter) developed by this paper's authors. The Advisory system determines the level of emotional state and work productivity integrally by employing three main biometric techniques (physiological, psychological and behavioral). By using these three biometric techniques, the Advisory system can analyze a person's eleven states of being (stress, work productivity, mood, interest in work) and seven emotions (self-control, happiness, anger, fear, sadness, surprise and anxiety) during a realistic timeframe. Furthermore, to raise the reliability of the Advisory system even more, it also integrated the data supplied by the Biometric Finger (blood pressure and pulse rates). Worldwide research includes various scientists who conducted in-depth studies on the different and very important areas of biometric mouse systems. However, biometric mouse systems cannot generate recommendations. The Advisory system determines a user's physiological, psychological and behavioral/movement parameters based on that user's real-time needs and existing situation. It then generates thousands of alternative stress management recommendations based on the compiled Maslow's Pyramid Tables and selects out the most rational of these for the user's specific situation. The information compiled for Maslow's Pyramid Tables consists of a collection of respondent surveys and analyses of the best global practices. Maslow's Pyramid Tables were developed for an employee working with a computer in a typical organization. The Advisory system provides a user with a real-time assessment of his/her own productivity and emotional state. This article presents the Advisory system, a case study and a scenario used to test and validate the developed Advisory system and its composite parts to demonstrate its validity, efficiency and usefulness.     

医院信息系统持续使用意愿研究——基于技术接受模型和期望确认理论

基于技术接受模型与期望确认理论,从患者视角对医院信息系统持续使用意愿进行了实证研究。结果显示感知易用性、感知可用性和系统满意度对系统持续使用意愿均有显著影响。其中感知易用性是最关键的影响因素,期待满足度也通过对感知可用性和系统满意度的作用来对系统持续使用意愿产生影响。基于研究结果,提出了进一步推进医院信息化与信息管理水平的若干建议。     

Empirical study of the dynamic behavior of JavaScript objects

Despite the popularity of JavaScript for client‐side web applications, there is a lack of effective software tools supporting JavaScript development and testing. The dynamic characteristics of JavaScript pose software engineering challenges such as program understanding and security. One important feature of JavaScript is that its objects support flexible mechanisms such as property changes at runtime and prototype‐based inheritance, making it difficult to reason about object behavior. We have performed an empirical study on real JavaScript applications to understand the dynamic behavior of JavaScript objects. We present metrics to measure behavior of JavaScript objects during execution (e.g., operations associated with an object, object size, and property type changes). We also investigated the behavioral patterns of observed objects to understand the coding or user interaction practices in JavaScript software. Copyright © 2015 John Wiley & Sons, Ltd.     

The influence of goal clarity,curiosity, and enjoyment on intention to code

The purpose of this study is to examine the influence of goal clarity, curiosity, and enjoyment – dimensions of flow theory – on the intention to write programming code. This research refines and extends previous information systems (IS) research in two significant ways: first, this research is focused specifically on systems development behaviour; second; this is the first research that isolates specific flow theory constructs associated with systems development behaviour. We used SmartPLS to test our model, as partial least squares is the appropriate statistical methodology for theory building and model testing. Findings are based on survey data from computer IS classes at two different universities. Goal clarity and curiosity independently and significantly contributed to enjoyment when programming, which significantly and positively influenced a future intention to code. Recommendations for practitioners and faculty include testing for curiosity characteristics, providing clear goals, and providing stimuli to pique curiosity.     

Continuance usage of corporate SNS pages: A communicative ecology perspective

This study develops a research model that explains the continuance of corporate social network service (SNS) pages. In order to find antecedents that influence end users’ continuance intention, this study adopts communicative ecology theory from media and communication studies. Results indicate that the quality of social interaction is the most salient feature, as indicated by the fact that it has the highest impact on perceived usefulness and enjoyment. Moreover, content quality also increases both perceived usefulness and enjoyment, while SNS platform quality and service quality increase perceived usefulness only. In addition, perceived network size moderates the impact of social interaction quality on perceived enjoyment.