心理因素与学业表现：机器学习分类预测模型

随着高等教育规模的扩大,学业表现不良逐渐成为一个不容忽视的现象,对学业表现不良的学生进行预测并提早给予干预可降低退学率并减少教育资源的损失。由于导致学业表现不良的因素众多且关系复杂,传统的基于相关分析的研究方法很难建立早期预测模型并进行应用。本研究旨在利用机器学习算法,对数据进行挖掘,并建立学业表现预测模型。研究对653名大一新生的心理健康状况、应对方式、人格、内外控倾向和相关人口统计学信息进行了收集,并在一年后采集了其学业成绩,利用随机森林(RF)、K邻近（KNN）、支持向量机（SVM）、决策树（DT）、朴素贝叶斯（NB）等机器学习算法建立了分类模型。结果显示,随机森林算法在识别学业表现不良学生时有最好的表现,其中准确率95.86%, 召回率91.83%,f1分数为93.80%。特征重要性分析显示,前10个对模型有最高贡献度的特征包括：年龄、性别、是否为独生子、内外控倾向、神经质倾向、积极应对倾向、宜人性倾向、一般症状指数、开放性倾向和焦虑水平。为避免过度拟合问题,本研究在一年后收集的166名新生样本中进行了模型验证,结果显示模型在新数据集上有较好的泛化表现,其中f1分数90.90％,准确率92.60％,召回率89.26％。研究提示基于人口统计学和心理测评信息,机器学习算法有助于及早识别学业表现不良学生并为开展早期干预提供启示。     

Atmospheres of street performance in Taipei: Affect and emotion as dynamic,simultaneous, more-than-representational experiences

Studies of street performance have highlighted its potential for creating vibrant and inclusive urban places, yet have largely neglected its atmospheric, affectual and emotional dimensions. Building on a growing body of work on atmospheres and dynamics of affect and emotion, I examine the formation of atmospheres by street performances in Taipei and its affectual and emotional resonance on space and people. I used an experimental more-than-representational methodology, including implementing a live survey questionnaire through the audience's smartphones during a performance. An atmosphere of street performance is generated through the lively interactions between the street performer, members of the audience, performance objects and the wider urban environment. Performance objects and the urban streetscape are vitalised as part of street performance, and have excessive potential in producing atmospheres. The spatio-temporal dimension of performance atmosphere is significant in generating memories and creating a therapeutic atmospheric space, experienced affectually and emotionally. I suggest that it would be helpful to see atmosphere and its affectual and emotional impact as dynamic, simultaneous experiences that people encounter as they are enmeshed within an atmosphere, such as in more-than-individual experiences or unexpected events. Within a changing atmosphere, there are multiple layers of affective and emotional outcomes, whether felt and emerging individually, and/or felt and emerging collectively.     

Improved Test–retest Reliability Criteria as Applied to Probability Assessments

Test–retest reliability is a common indicator of response consistency. It is argued that using regression coefficients for detecting systematic response error is less appropriate than testing for shifts in the mean (median) and variance. This procedure is exemplified using probability response data. For this data, shifts in centrality were found to be about 2.5 times more likely than shifts in variability. The shifts in centrality did not favor any particular direction; however, variability tended to decrease over time in early sessions.     

Effects of prior agonistic experience on risk assessment and approach behavior evoked by familiar or unfamiliar conspecific odors

Risk assessment and appetitive behaviors in response to familiar and unfamiliar conspecific odors were measured in mice rendered dominant or subordinate by a series of resident-intruder encounters. Subordinate mice showed elevated levels of risk assessment in response to the odors of both familiar dominant and unfamiliar males. These behaviors were almost totally absent among dominant males exposed to familiar subordinate or unfamiliar male odors. Subordinate mice showed a marginally significant elevation in latencies to approach familiar, but not unfamiliar, dominant odors. Dominant and subordinate mice spent comparable amounts of time in the cage area containing familiar antagonist odors, however, and the durations of subordinates were mildly elevated, rather than decreased, when unfamiliar conspecific odors were present. There were no group differences in any of the appetitive behaviors. These findings suggest that apparent preferences for conspecific odors may arise from quantitatively and/or qualitatively differing emotional states. The inclusion of risk assessment measures is suggested to be a useful adjunct for studies of olfactory preference/rejection. © 1994 Wiley-Liss, Inc.     

One Roof,Three Generations: Grandparental Co-residence and Child Outcomes in China

This study examined the association between grandparental co-residence and child academic and behavioral outcomes using a sample from Shanghai, China (n = 1,763), and was built on two theoretical perspectives: intergenerational solidarity theory and the contextual model of family stress. These models integrate the impact of residential and relational proximity to grandparents on child well-being and underscore the importance of family context. This study also explored the moderating effects of family resources using proxies that prior theoretical and empirical studies have found to be important to such associations: family income, parental education, hukou status, and subjective social status. Results indicated that among families without co-residing grandparents, rural and low-income parents reported their children to have more externalizing behavioral issues than their respective urban and non-low-income counterparts. In addition, children who resided in poorly resourced families (i.e., low family income, low parental education, low subjective social status, or rural hukou status) tended to benefit from living with grandparents compared to their well-resourced counterparts in terms of lower externalizing and internalizing behaviors reported by teachers. These results do not negate the potential beneficial effects of living with grandparents for children in well-resourced environments. Implications for practice and policy, as well as future research directions, are discussed.     

Comparison of contingent and noncontingent access to therapy dogs during academic tasks in children with autism spectrum disorder

This study compared contingent and noncontingent access to therapy dogs during educational tasks for children with autism spectrum disorder using a multielement design. The experimenters assessed whether initial preference for the dog predicted reinforcer efficacy and how preference changed across time. A higher response rate during contingent dog sessions than baseline sessions occurred for 4 out of 5 participants, suggesting that the dog functioned as a reinforcer. One participant engaged in a high rate of responding in both contingent and noncontingent dog conditions. Preference assessments revealed idiosyncrasies, suggesting that further research is needed into the predictive nature of initial preference assessments with animals as part of the stimulus array. The experimenters also analyzed salivary cortisol before and after sessions to determine if learning about the upcoming interaction with a dog reduced salivary cortisol in children. Cortisol was variable across participants, with only some deriving a potential physiological benefit from expecting to interact with the dog.     

Assessment to identify learner-specific prompt and prompt-fading procedures for children with autism spectrum disorder

Few studies have evaluated the use of assessment to identify the most efficient instructional practices for individuals with autism spectrum disorder. This is problematic as these individuals often have difficulty acquiring skills, and the procedures that may be efficient with one individual may not be for others. The experimenters conducted instructional assessments to identify the most efficient prompt type (model, partial physical, full physical) and prompt-fading procedure (progressive delay, most-to-least, least-to-most) for teaching auditory–visual conditional discriminations for individuals with autism spectrum disorder. Each assessment was conducted at least twice, and a final generality test combined the most and the least efficient prompt type and prompt-fading procedure for teaching novel auditory–visual conditional discriminations. The results demonstrated learner-specific outcomes for the prompt type assessment, whereas the least-to-most prompt fading procedure was most efficient for all participants.     

The Performance Diagnostic Checklist-Human Services: A brief review

The Performance Diagnostic Checklist-Human Services (PDC-HS) is an informant-based tool designed to identify the variables contributing to poor employee performance in human service settings, such as clinics, schools, and residential facilities. Upon completion of the tool, an intervention indicated by PDC-HS results is used to improve employee performance. To date, the PDC-HS has been used in a number of studies. This review describes the existing research on the PDC-HS and provides suggestions for future research.     

A comparison of picture and GIF-based preference assessments for social interaction

Researchers have recently begun to evaluate video-based preference assessments; however, only two studies have evaluated the efficacy of this preference assessment modality in assessing preference for social interactions. Four individuals diagnosed with autism spectrum disorder who could not match pictures or graphic-interchange-format images (GIFs) of social interactions to in vivo interaction participated. We compared picture and GIF-based paired-stimulus preference assessments for social interaction and evaluated the preference assessment hierarchies by conducting a concurrent-operant reinforcer assessment including all social interactions. The GIF-based preference assessment produced similar hierarchies to the reinforcer assessment for all participants, whereas the picture-based preference assessments produced similar hierarchies to the reinforcer assessment for 2 of 4 subjects. Additionally, we conducted a modality preference assessment in which we evaluated participants' preference for viewing GIFs or pictures of social interactions, and found that 3 out of 4 subjects displayed a preference for GIFs.     

Evaluation of an indirect assessment for identifying tasks for functional analysis

Although a demand analysis is helpful for identifying potential establishing operations for the functional analysis (FA) demand condition, it may not always be practical due to time constraints. A potential alternative is the Negative Reinforcement Rating Scale (NRRS), an indirect assessment tool that may serve as a time efficient alternative to a demand analysis. The experimenter assessed the reliability and validity of the NRRS for 5 individuals with autism spectrum disorder who exhibited problem behavior. Multiple types of interrater reliability were assessed across 2 informants, and NRRS outcomes were compared to a subsequent demand analysis and FA to assess its validity. Reliability was high (M = 84%) for NRRS numerical ratings of categories but low (M = 32.9%) for specific examples provided. NRRS-identified highly aversive tasks yielded better correspondence with demand analysis outcomes than did NRRS-identified less aversive tasks.