Compensation paradox: the influence of monetary rewards on user behaviour

Many e-commerce companies collect users’ personal data for marketing purposes despite privacy concerns. Information-collecting companies often offer a monetary reward to users to alleviate privacy concerns and ease the collection of personal information. This study focused on the negative effects of monetary rewards on both information privacy concerns (IPC) and information disclosure. A survey approach was used to collect data and 370 final responses were analysed using a two-way analysis of variance and a binomial logistic regression model. The results show that monetary rewards increase IPC when an information-collecting company requires sensitive information. Additional results indicate that building trust is a more effective way of collecting personal data. This study identifies how organisations can best execute information-collection activities and contributes additional insights for academia and practitioners.     

Gorillas (Gorilla gorilla) and Orangutans (Pongo pygmaeus) Encode Relevant Problem Features in a Tool-Using Task.

Two important elements in problem solving are the abilities to encode relevant task features and to combine multiple actions to achieve the goal. The authors investigated these 2 elements in a task in which gorillas (Gorilla gorilla) and orangutans (Pongo pygmaeus) had to use a tool to retrieve an out-of-reach reward. Subjects were able to select tools of an appropriate length to reach the reward even when the position of the reward and tools were not simultaneously visible. When presented with tools that were too short to retrieve the reward, subjects were more likely to refuse to use them than when tools were the appropriate length. Subjects were proficient at using tools in sequence to retrieve the reward. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Delay discounting of real and hypothetical rewards.

The degree to which real and hypothetical rewards were discounted across delays ranging from 6 hr to 1 year was explored in a within-subjects design. An adjusting-amounts procedure was used to estimate the subjective value of real and hypothetical rewards at each delay. A hyperbolic discounting function provided a significantly better fit to individual participants' preferences than did an exponential function. No significant effect of reward type on degree of hyperbolic discounting or area under the discounting curves was detected. These findings offer some support for the validity of using hypothetical rewards to estimate discounting rates in substance-abusing and other populations, but caution is suggested because this support is gleaned from a failure to detect an effect of reward type. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

"Does reward increase or decrease creativity?": Correction to Eisenberger and Selbst.

Reports an error in "Does reward increase or decrease creativity" by Robert Eisenberger and Michael Selbst (Journal of Personality and Social Psychology, 1994[Jun], Vol 66[6], 1116-1127). In the aforementioned article, Figures 1 and 2 were interchanged. The figures appear with their correct captions in the erratum. (The following abstract of the original article appeared in record 1994-40652-001.) Two studies involving 504 school children investigated why behaviorists and cognitively oriented investigators have come to opposite conclusions about reward's effects on creativity. A monetary reward for a high degree of divergent thought in 1 task (word construction) increased children's subsequent originality in a different task (picture drawing). The same reward, made contingent on a low degree of divergent thought, reduced this generalized originality. These effects were eliminated by using a large reward and were restored by keeping the large reward out of the children's sight. The results suggest that reward training increases generalized creativity when (1) a high degree of divergent thought is required and (2) the reward is presented in not too salient a fashion. The findings are consistent with a 2-factor interpretation of rewarded creativity effects that incorporates learned industriousness and selective attention. [A correction concerning this article appears in Journal of Personality & Social Psychology, 1994(Jul), Vol 67(1), 125. Figures 1 and 2 were interchanged.] (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Personalized course generation and evolution based on genetic algorithms

Online learners are individuals,and their learning abilities,knowledge,and learning performance differ substantially and are ever changing.These individual characteristics pose considerable challenges to online learning courses.In this paper,we propose an online course generation and evolution approach based on genetic algorithms to provide personalized learning.The courses generated consider not only the difficulty level of a concept and the time spent by an individual learner on the concept,but also the changing learning performance of the individual learner during the learning process.We present a layered topological sort algorithm,which converges towards an optimal solution while considering multiple objectives.Our general approach makes use of the stochastic convergence of genetic algorithms.Experimental results show that the proposed algorithm is superior to the free browsing learning mode typically enabled by online learning environments because of the precise selection of learning content relevant to the individual learner,which results in good learning performance.     

电子商务个性化推荐系统的构建

针对电子商务环境下,客户需求日趋差别化,构建个性化推荐系统,进而阐述该系统的功能及工作流程,并具体分析系统的结构,旨在更为有效地为客户推荐其所需信息。     

Agent-based architecture for context-aware and personalized event recommendation

In order to offer context-aware and personalized information, intelligent processing techniques are necessary. Different initiatives considering many contexts have been proposed, but users preferences need to be learned to offer contextualized and personalized services, products or information. Therefore, this paper proposes an agent-based architecture for context-aware and personalized event recommendation based on ontology and the spreading algorithm. The use of ontology allows to define the domain knowledge model, while the spreading activation algorithm learns user patterns by discovering user interests. The proposed agent-based architecture was validated with the modeling and implementation of eAgora? application, which was illustrated at the pervasive university context.     

基于深度学习的多元信息嵌入推荐模型

传统的矩阵分解法只能简单提取低阶信息,特征组合单一,无法挖掘更多隐含信息。依赖稀疏的评分表已经无法满足个性化推荐。MovieLens数据集是研究推荐系统的经典数据集。通过改进神经协同过滤模型,使用多个嵌入层对MovieLens数据集所有信息进行嵌入分析,充分挖掘隐含信息,使得推荐算法更有实用意义。通过在MovieLens-100k和MovieLens-1m上设置多组对照实验表明,该改进模型不仅学习了更多信息,而且与神经协同过滤模型相比,其错误率显著减小。     

一种改进的基于梯度提升回归算法的 O2O 电子商务推荐模型

位置属性对于线下消费的用户具有重要影响。为了有效提高个性化推荐精度,在对O2O电子商务特点进行用户特征分析的基础上,在推荐算法中引入当前时间参数和位置参数,提出了一种改进的基于梯度提升回归算法的O2O电子商务推荐模型。实验结果表明,改进的基于梯度提升回归算法的O2O电子商务推荐模型在实时性和准确性方面明显优于传统的推荐算法。     

基于神经网络的用户视频评分自动获取方法

在未来的智能电视系统中,真正的智能视频推荐应该是不需要用户评分动作就能自动、准确地获得用户兴趣、爱好并做出推荐的系统。研究无评分动作约束下的用户评分(揭示了他们的兴趣和爱好)自动获取技术是真正的智能推荐必须解决的一个关键问题。给出了一种基于神经网络的用户视频隐性评分自动获取方法。基于用户视频观看行为与评分样本的实验结果表明,该方法可以有效地获取用户的隐性评分信息。