A reinforcement learning approach to personalized learning recommendation systems

Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data-driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.     

Social decision making mediates the association between anger and externalising problems in Chinese adolescents

The goal of this study was to test the mediating effect of social decision making in the relations of anger and anger control to externalising and internalising problems. A sample of 174 Chinese adolescents (mean age = 15.36 years) completed self‐reports of trait anger, anger control, externalising problems, internalising problems and social decision making, which was operationalized as situational judgement reflecting an individual's ability to interact effectively with parents, teachers and peers. Findings indicated that adolescents' trait anger and anger control were positively related to both externalising and internalising problems. In addition, path analysis revealed that social decision making mediated the relationship between trait anger, anger control and externalising problems. Findings on the mediating effect will be discussed by referencing appraisal tendency theory and response evaluation and decision.     

Relationships between Sabbath Observance and Mental,Physical, and Spiritual Health in Clergy

Pastoral Psychology - Keeping the Sabbath, that is, setting a day apart for rest and spiritual rejuvenation, has been related to better mental health and less stress in cross-sectional studies....     

Restricted Recalibration of Item Response Theory Models

Psychometrika - In item response theory (IRT), it is often necessary to perform restricted recalibration (RR) of the model: A set of (focal) parameters is estimated holding a set of (nuisance)...     

理解双人肢体运动表达的友好和敌对意图的ERP证据

已有的意图理解神经成像研究大多关注理解单一个体的中性或负性意图的脑功能定位, 而大脑理解依靠双人肢体运动表达的友好和敌对意图的动态时间过程尚不清楚。本研究记录了20名健康被试完成三种不同意图推理任务时的脑电成分。三种意图分别为：1)友好意图; 2)敌对意图; 3)中性无互动意图。行为结果发现理解敌对意图的反应时最短。电生理学结果表明, 在额中区的N250 (170~270 ms)上, 中性意图比友好和敌对意图均更负, 且友好意图比敌对意图也更负; 在大脑右半球的P300 (270~450 ms)上, 敌对意图比友好和中性意图均更正, 且友好意图比中性意图也更正。对友好和敌对意图的N250和P300进行溯源分析分别定位于额中回(BA10)和脑岛(BA45)。结果表明大脑在多个阶段对双人肢体运动表达的互动意图进行分类理解, 对负性敌对意图表现出较早的理解且晚期持续性的评价加工。     

“没有”为什么隐含着“消极情绪”?——否定加工中的情绪表征

采用情感错误归因范式(AMP)和经典情感启动范式(BFP), 在汉语双音节中性名词的前面加上否定或肯定词, 构成“没有/有XX”短语, 作为启动材料, 以中性俄语词或汉语情绪词为目标材料, 探讨了汉语否定加工的情绪表征。在实验1的AMP范式中, 刺激反应不同步(SOA)时间为200 ms和500 ms, 结果显示, 否定短语比肯定短语有显著高的消极反应概率; 在实验2的BFP范式中, 否定短语比肯定短语同样启动了更高的消极反应概率。实验结果表明, 否定本身具有消极效价, 否定加工通过消极情绪实现具身化。     

On the Implicit Anaphoric Argument of Relational Nouns in Mandarin Chinese

Journal of Psycholinguistic Research - This paper provides experimental and theoretical evidence for the syntactic realization of an implicit possessor argument in Relational Nouns (RNs, e.g....     

类别标签与典型性程度对类别特征推理的影响

本研究采用学习-测试二阶段实验范式,探讨了类别标签及典型性程度对类别特征推理任务的共同影响,结果表明,类别标签及典型性程度都会影响类别特征推理任务,而且,类别标签及典型性程度之间存在交互作用,典型性程度为高条件下类别标签对类别特征推理任务的影响要高于典型性程度为低条件,类别标签匹配条件下,典型性程度对类别特征推理任务的影响要高于类别标签不匹配条件。     

青少年学生焦虑敏感与睡眠质量的关系及其内在机制

采用中学生、大学生焦虑敏感问卷和匹兹堡睡眠质量指数量表(PSQI),分别对1011名中学生和607名大学生进行调查。结果显示高焦虑敏感学生的PSQI总分显著高于低焦虑敏感学生,焦虑敏感及其三个因子与PSQI的相关都是中效应,焦虑敏感对青少年学生睡眠质量指数具有显著的正向预测作用,焦虑敏感水平越高,其睡眠质量越差。焦虑敏感可能以应激事件和健康问题作为致敏源,以焦虑等负性情绪作为敏感内容,在消极自动认知觉察与思维的介入下,进一步放大对有关负性情绪的感受与体验,从而影响青少年学生的睡眠质量。     

Temporal and spatial control following bilateral versus unilateral training

Principles of motor control and learning such as bilateral coordination and task-specificity, are increasingly incorporated in the design of upper extremity rehabilitation protocols for stroke survivors. Yet most studies investigating the efficacy of new protocols report composite scores of standardized tests, such as the Fugl-Meyer Upper Extremity test (FM) and the Wolf Motor Arm Test, rather than determining how the motor control and coordination of arm movements has changed. Here we present a sub-study of a larger randomized controlled trial comparing a bilateral and unilateral training protocol where participants were assessed on bilateral and unilateral arm reaching. Eligible participants for the arm reaching analysis were 9 (FM=37) and 9 (FM=34) in Bilateral Arm Training with Rhythmic Auditory Cueing (BATRAC) and Dose Matched Therapeutic Exercises (DMTE), respectively. Participants undertook 18 sessions of training for 6 weeks with 20min of active training per session. For bilateral arm reaching, participants after BATRAC were faster, with increased peak acceleration, fewer movement units, and smoother hand paths for each arm. The BATRAC training group showed greater improvements with training than the DMTE group during bilateral reaching for parameters of movement units and smoothness of hand path. For unilateral arm reaching, participants were faster after DMTE for paretic arm reaching; however, this group did not improve to a greater extent than the BATRAC training group. Within group functional gains were seen after BATRAC on FM, Wolf Motor Arm Test (time and weight) and after DMTE on FM and Wolf Weight. There was a positive correlation between movement units and the time component of the Wolf Motor Arm Test. The reaching analysis demonstrates task-specificity in training since BATRAC improves performance in bilateral reaching and DMTE improves performance in unilateral reaching. Temporal/spatial control outcomes in studies of post-stroke interventions can identify functionally relevant motor control changes that are not captured by traditional standardized tests.