双模态情感分析的弹幕网络视频平台营销策略

随着互联网飞跃发展, 弹幕视频应运而生。这种新型的用户与视频交互方式具有新特性, 如用户情感表达实时动态性、情感分布多峰性。同时, 新特性也给实际研究工作带来挑战, 如用户画像刻画难度增大, 视频推荐和广告推送所需精度提高。现有研究尚未对弹幕视频的新特性进行深入分析, 也没有充分挖掘其本身所蕴含的学术研究价值。本文利用深度学习、自然语言处理技术、系统动力学方法, 结合心理学、市场营销学等多学科交叉前沿知识, 从数据驱动角度对弹幕视频数据进行分析和建模, 深度挖掘视频大数据潜在的商业价值。重点研究弹幕与视频双模态融合的情感识别方法; 构建带有用户情感特征的动态用户画像, 并建立基于用户画像的网络视频粘性营销机制; 分析用户情感与视频广告插播方式的相关性, 提出视频广告动态插播策略。丰富现有研究的同时, 为网络视频企业准确定位与分析用户需求, 创建高品质的智能营销平台供理论与决策支持。     

Therapist Interventions and Skills as Predictors of Dropout in Outpatient Psychotherapy

The current study employed machine learning to investigate whether the inclusion of observer-rated therapist interventions and skills in early sessions of psychotherapy improved dropout prediction beyond intake assessments. Patients were treated by postgraduate clinicians at a university outpatient clinic. Psychometric instruments were assessed at intake and therapeutic interventions and skills in the third session were routinely rated by independent observers. After variable preselection, an elastic net algorithm was used to build two dropout prediction models, one including and one excluding observer-rated session variables. The best model included observer-rated variables and was significantly superior to the model including intake variables only. Alongside intake variables, two observer-rated variables significantly predicted dropout: therapist use of feedback and summaries and treatment difficulty. Although not retained in the final prediction model, the observer-rated use of cognitive techniques was also significantly correlated with dropout. Observer ratings of therapist interventions and skills in early sessions of psychotherapy improve predictors of dropout from psychotherapy beyond intake variables alone. Future research could work toward personalizing dropout predictions to the specific dyad, thereby improving their validity and aiding therapists to recognize and react to increased dropout risk.     

Comparing instructor-led,video-model,and no-instruction control tutorials for creating single-subject graphs in Microsoft Excel: A systematic replication and extension

Visual inspection of single-subject data is the primary method for behavior analysts to interpret the effect of an independent variable on a dependent variable; however, there is no consensus on the most suitable method for teaching graph construction for single-subject designs. We systematically replicated and extended Tyner and Fienup (2015) using a repeated-measures between-subjects design to compare the effects of instructor-led, video-model, and no-instruction control tutorials on the graphing performance of 81 master's students with some reported Microsoft Excel experience. Our mixed-design analysis revealed a statistically significant main effect of pretest, tutorial, and posttest submissions for each tutorial group and a nonsignificant main effect of tutorial group. Tutorial group significantly interacted with submissions, suggesting that both instructor-led and video-model tutorials may be superior to providing graduate students with a written list of graphing conventions (i.e., control condition). Finally, training influenced performance on an untrained graph type (multielement) for all tutorial groups.     

Eye-gaze behaviour of expert and novice surfers in a simulated surf environment

Skilled performance in sport often relies on looking at the right place at the right time. Differences in visual behaviour can thus characterise expertise. The current study examined visual attention associated with surfing expertise. Expert (n = 12) and novice (n = 12) surfers viewed 360-degree surfing videos in a head-mounted display. Eye-gaze, presence, and engagement were measured. Experts were faster to detect approaching high, and low waves, spent more time overall attending to high-performance value areas-of-interest (AOIs; pocket, shoulder, lip), and were more physically engaged. Group differences were not found for presence or simulator sickness. Outcomes show that surfing expertise is associated with more optimal visual attention to cues informing wave approach and wave dynamics. Experts look at these areas earlier than novices, and for more time overall. The findings suggest the performance advantages of early planning of motor actions, along with moment-to-moment adjustments while surfing.     

暴力视频游戏接触对大学生网络攻击行为的影响：一个有中介的调节模型

以946名大学生为被试进行问卷调查,探讨暴力视频游戏接触对大学生网络攻击行为的影响机制。结果表明：(1) 暴力视频游戏接触正向预测大学生网络攻击行为;(2) 特质愤怒在大学生暴力视频游戏接触与其网络攻击行为及暴力态度的关系中均具有调节作用;(3) 暴力态度不仅部分中介了大学生暴力视频游戏接触对其网络攻击行为的影响,而且部分中介了特质愤怒与暴力视频游戏接触的交互作用对大学生网络攻击行为的影响。     

测验与反馈在分段视频学习中的作用

分段原则是多媒体和视频学习中通过分段促进学习的重要原则。本研究探讨了测验和反馈对分段的影响。实验1对比了观看分段视频和在分段中进行测验两种情境,结果表明分段中测验会提高学习表现。实验2对比了分段视频、分段中测验和分段中测验并提供反馈三种情境。结果发现分段组与分段测验组之间没有差异,接受反馈的学习者学习表现最好。结果表明在分段视频中测验和反馈具有积极效应,对多媒体和线上学习具有潜在的意义。     

Preliminary investigation of a video-based stimulus preference assessment

Video clips may be an effective format for presenting complex stimuli in preference assessments. In this preliminary study, we evaluated the correspondence between preference hierarchies generated from preference assessments that included either toys or videos of the toys. The top-ranked item corresponded in both assessments for 5 of the 6 participants, and the top- and bottom-ranked items corresponded for 4 participants. The implications of these results for future research on video preference assessments are discussed.     

The effects of video modeling with voiceover instruction on accurate implementation of discrete-trial instruction

The present study replicates and extends previous research on the use of video modeling (VM) with voiceover instruction to train staff to implement discrete-trial instruction (DTI). After staff trainees reached the mastery criterion when teaching an adult confederate with VM, they taught a child with a developmental disability using DTI. The results showed that the staff trainees' accurate implementation of DTI remained high, and both child participants acquired new skills. These findings provide additional support that VM may be an effective method to train staff members to conduct DTI.     

Personality traits associated with problematic and non-problematic massively multiplayer online role playing game use

This research investigated the associations between personality traits and both normal and problematic massively multiplayer online role playing game (MMORPGs) play, as measured by a self report scale. A total of 225 participants completed the online questionnaire, 66 of whom played MMORPGs. Correlational analyses indicated that low levels of functional impulsivity and agreeableness alongside high levels of verbal aggression and video game dependency were associated with greater amount of time spent playing MMORPGs. When comparing problematic and non-problematic MMORPG players directly, problematic players were found to be lower in self regulation, dysfunctional impulsivity and agreeableness, suggesting that these traits may be important in the development and maintenance of problematic MMORPG use.