基于弹幕情感分析和主题模型的视频推荐算法

针对互联网上大量自制视频缺少用户评分、推荐准确率不高的问题,提出一种融合弹幕情感分析和主题模型的视频推荐算法（VRDSA）。首先,对视频的弹幕评论进行情感分析,得到视频的情感向量,之后基于情感向量计算视频之间的情感相似度;同时,基于视频的标签建立主题模型来得到视频标签的主题分布,并使用主题分布计算视频之间的主题相似度;接着,对视频的情感相似度和主题相似度进行融合得到视频间的综合相似度;然后,结合视频间的综合相似度和用户的历史记录得到用户对视频的偏好度;同时通过视频的点赞量、弹幕量、收藏数等用户互动指标对视频的大众认可度进行量化,并结合用户历史记录计算出视频的综合认可度;最后,基于用户对视频的偏好度和视频的综合认可度预测用户对视频的认可度,并生成个性化推荐列表来完成视频的推荐。实验结果表明,与融合协同过滤和主题模型的弹幕视频推荐算法（DRCFT）以及嵌入LDA主题模型的协同过滤算法（ULR-itemCF）相比,所提算法推荐的准确率平均提高了17.1%,召回率平均提高了22.9%,F值平均提高了22.2%。所提算法对弹幕进行情感分析,并融合主题模型,以此来完成对视频的推荐,并且充分挖掘了弹幕数据的情感性,使得推荐结果更加准确。     

Exploring Online Learners' Interactive Dynamics by Visually Analyzing Their Time‐anchored Comments

MOOCs (Massive Open Online Courses) are increasingly prevalent as an online educational resource open to everyone and have attracted hundreds of thousands learners enrolling these online courses. At such scale, there is potentially rich information of learners' behaviors embedded in the interactions between learners and videos that may help instructors and content producers adjust the instructions and refine the online courses. However, the lack of tools to visualize information from interactive data, including messages left to the videos at particular timestamps as well as the temporal variations of learners' online participation and perceived experience, has prevented people from gaining more insights from video‐watching logs. In this paper, we focus on extracting and visualizing useful information from time‐anchored comments that learners left to specific time points of the videos when watching them. Timestamps as a kind of metadata of messages can be useful to recover the interactive dynamics of learners occurring around the videos. Therefore, we present a visualization system to analyze and categorize time‐anchored comments based on topics and content types. Our system integrates visualization methods of temporal text data, namely ToPIN and ThemeRiver, which can help people understand the quality and quantity of online learners' feedback and their states of learning. To evaluate the proposed system, we visualized time‐anchored commenting data from two online course videos, and conducted two user studies participated by course instructors and third‐party educational evaluators. The results validate the usefulness of the approach and show how the quantitative and qualitative visualizations can be used to gain interesting insights around learners' online learning behaviors.     

基于弹幕情感分析和聚类算法的视频用户群体分类

随着数字媒体等技术的发展,出现了弹幕系统这种新型的评论模式并逐渐流行。它能够使视频观众即时发布关于视频情节内容的评论,也可以帮助观众理解视频内容。弹幕文本数据的产生,为短文本处理和实时数据处理提供了新的素材。研究弹幕数据的特点和其表达的情感,可以帮助我们更好地理解视频情节;研究弹幕内容之间的相似度进而分析用户之间的关联关系,不仅能够深入了解弹幕用户的特点、发掘不同视频之间的潜在联系,而且可以为视频制作时受众群体的选择提供更为准确的解决方案。首先将弹幕文本数据进行收集和预处理,然后计算这些文本的情感值。针对弹幕文本口语化的特点,建立了网络弹幕常用词词典。通过改进传统的k-means聚类算法,对所有发表弹幕的用户进行基于情感值的分类。这样的分类可以帮助我们了解观看特定类型视频的观众在情感上的异同点。     

移动互联网视频传输优化的架构研究

随着3G移动互联网的快速发展,在手机等移动终端上看视频成为一种日常应用.但互联网上的大部分视频对于移动用户而言,其码率相对较大,而且移动用户的可用带宽受环境影响变化大,不稳定,影响了用户观看视频的体验.提出一种针对移动互联网的视频传输优化解决方案的系统架构,该架构从缓存和压缩两个方面入手,通过缓存缓解运营商的骨干网流量压力,通过视频压缩降低视频码率以满足用户的实际接入带宽.该架构既为运营商节约了带宽、降低了运营成本,同时也保证用户观看视频的连续性,提高用户体验.     

Discrimination of media moments and media intervals: sticker-based watch-and-comment annotation

In this paper we discuss the problem of how to discriminate moments of interest on videos or live broadcast shows. The primary contribution is a system which allows users to personalize their programs with previously created media stickers??pieces of content that may be temporarily attached to the original video. We present the system??s architecture and implementation, which offer users operators to transparently annotate videos while watching them. We offered a soccer fan the opportunity to add stickers to the video while watching a live match: the user reported both enjoying and being comfortable using the stickers during the match??relevant results even though the experience was not fully representative.     

Breaking news: “I have an eating disorder.” Video testimonials on YouTube

Over the last several decades there has been an exponential increase in the usage of the Internet, and social networking websites in particular. Social networking websites have gained popularity because they allow people to network on both a personal and professional level. The rise of testimonial videos about one’s experience with hardships has gained popularity as another way for people to connect with one another for support. The current study looks at men and women who utilized YouTube, a video posting website, to document their struggles with eating disorders (ED). Fifty videos were viewed and analyzed regarding content and viewer response. It was found that most posters actively sought treatment for their ED, yet sought out additional support on the Internet while also offering support for others. In addition, viewers responded with an overwhelmingly large number of supportive comments compared to negative comments (8:1).     

Smartphones or laptops in the collaborative classroom? A study of video-based learning in higher education

This paper explores how the use of smartphones vs. laptops influences students’ engagement, behaviour and experience watching academic videos in a collaborative classroom. Experiments were run in authentic teaching sessions with a total of 483 first-year higher education students. The methodology applied is a quasi-experimental design with post-test-only, being the independent variable, the device used to visualise the academic videos. Results indicate that the use of laptops has provided better results in terms of student’s engagement with the videos, their collaborative behaviour and satisfaction with the device. Hence, the findings of this research suggest that the type of mobile device used in activities that consider the use of videos in a collaborative class need to be carefully chosen to maximise the student’s comfortability – and in consequence, their engagement with the video-based learning activity and their positive behaviour and experience within the collaborative context.     

Incorporating user motivations to design for video tagging

User video tagging can enhance the indexing of large collections of videos, or can provide the basis for personalizing output. However, before the benefits of tagging can be reaped, users must be motivated to provide videos with tags. This article describes a two-stage study that aimed at collecting the most important motivations for users to tag video material. First, focus groups with internet users were held to elicit all possible motivations to tag videos on the internet. Next, 125 persons ranked these motivations for two cases via an online survey and responded to statements that assessed their acceptance of personalized output, based on their tags. Motivations related to indexing appear to be far more important for people than motivations related to socializing or communication. Furthermore, people were moderately positive about personalized output, based on their tags. Finally, important user barriers to tagging are discussed.     

Who’s Watching You?

A cold clammy feeling, your neck hair rising and an increased level of twitchiness. I’m sure most readers will have had this experience when they feel that inexplicably, and often illogically, someone is watching them. Unfortunately for some people this is real — stalkers, both in the real and cyber-world do exist and you need to know what to do if and when it happens to your company.     

Facilitating Students’ Interaction in MOOCs through Timeline-Anchored Discussion

ABSTRACT

Interaction is central to any learning experience. Currently, Massive Open Online Courses (MOOCs) rely on discussion forums as a primary means of interaction among learners and instructors. Threaded discussions of such forums help learners to hold an ongoing and recursive discussion over an extended period, but the lack of temporal and spatial contiguity makes it insufficient to deliver a smooth interaction experience. To facilitate such interaction, this study designed DanMOOC, a commenting tool that facilitates timeline-anchored discussion among MOOC learners and instructors. DanMOOC was the first to combine threaded discussions with Danmaku commenting, a video commenting feature that allows viewers of the same video to share comments at the top of the video screen. The design process followed an iterative process of user-centered design. The impact of the new design on learning was assessed empirically through a laboratory experiment comparing DanMOOC with the current MOOC system (video-based learning + forum). The results show that DanMOOC increases learners’ perceptions of social, teaching, and cognitive presence, engages learners more in discussion, and improves learners’ satisfaction with both the course and the platform.     

Using 360‐degree videos in teacher education to improve preservice teachers' professional interpersonal vision

Noticing and interpreting classroom events (professional vision) is an important element of preservice teachers' (PSTs) interpersonal competence. This paper presents a mixed‐method study about a classroom simulation using 360‐degree videos combined with theoretical lectures in teacher education, intended to improve PSTs' interpretations of noticed events. Furthermore, this study examined how PSTs evaluate technological and educational affordances of 360‐degree videos. Results indicate that participating PSTs improved in noticing classroom events and in applying a more theory‐based terminology to describe these events. PSTs perceived observing other teachers teach as an educational affordance for mastering theory and for developing insights about interpersonal teacher behaviour. Concerning technological affordances, mainly physical discomforts and technical hindrances, was reported by PSTs. The results of this study imply that 360‐degree videos can be useful for teacher education to improve PSTs' interpretation of noticed events.     

基于NPTB模型的影视网站影片推广组合预测

在结合影视观众基本信息的前提下,针对影视网站新上线收费影片的类型,本文提出在NPTB(Next-Product-toBuy)模型的基础上融入组合预测模型,用来预测影视观众下一部可能接受观看的影片概率,在此基础上选择观看此类型影片概率最高的观众进行影片推广,以期达到影视网站盈利的目的。实验表明,本研究所用模型明显优于其它预测观众观看影片概率的模型。     

Collaborative Interaction for Videos on Mobile Devices Based on Sketch Gestures

With the rapid progress of the network and mobile techniques, mobile devices such as mobile phones and portable devices, have become one of the most important parts in common life.Efficient techniques for watching, navigating and sharing videos on mobile devices collaboratively are appealing in mobile environment.In this paper, we propose a novel approach supporting efficiently collaborative operations on videos with sketch gestures.Furthermore, effective collaborative annotation and navigation operations are given to interact with videos on mobile devices for facilitating users’ communication based on mobile devices’ characteristics.Gesture operation and collaborative interaction architecture are given and improved during the interactive process.Finally, a user study is conducted showing that the effectivity and collaborative accessibility of video exploration is improved.     

基于内容的监视视频摘要技术研究

介绍了视频摘要的相关概念、作用以及视频摘要所涉及到的一些关键技术,探讨了视频结构化的主要步骤,在分析监视视频特征的基础上,给出了一个基于内容的监视视频摘要系统模型。     

基于内容的监视视频摘要技术研究

介绍了视频摘要的相关概念、作用以及视频摘要所涉及到的一些关键技术,探讨了视频结构化的主要步骤,在分析监视视频特征的基础上,给出了一个基于内容的监视视频摘要系统模型。     

融合评论分析和隐语义模型的视频推荐算法

针对网络视频元数据信息缺失严重和多媒体数据本身特征难以提取等问题,提出了融合评论分析和隐语义模型的网络视频推荐算法.从视频评论入手,通过分析用户对不同视频的评论内容以判断其情感倾向并加以量化,继而构建用户对项目的虚拟评分矩阵,弥补了显式评分数据稀疏性问题.考虑到网络视频的多元性和高维度特性,为了深度挖掘用户对网络视频的潜在兴趣,针对虚拟评分矩阵采用隐语义模型(LFM)对网络视频分类,在传统的用户—项目二元推荐系统基础之上添加虚拟类目信息以进一步发掘用户—类目—项目关联关系.实验在多重标准下进行,对YouTube评论集的实验表明,所提推荐方法获得了较高的推荐精度.     

基于车载视觉的驾驶员后视镜查看行为检测

车辆转向时驾驶员的后视镜查看行为是行车安全的必要措施之一，但目前关于该 行为的检测技术应用尚属空白。为督促驾驶员在车辆转向时及时查看后视镜留意车辆侧后方的 交通情况，基于车载单目视觉与图像处理技术提出一种自适应检测方法。首先，设计帧差搜索 分割算法自动实现车辆启动期间的驾驶员脸颈初始区域定位和灰度初值计算，摆脱算法对驾驶 员信息的依赖；设计胀缩分割算法快速实现车辆行驶期间的驾驶员脸颈区域定位和灰度均值计 算。其次，提取脸颈外轮廓并定义了一种由颈部轮廓基点垂线划分的左右面积比特征参数，分 析表明其受驾驶员头部姿态显著影响。最后，结合驾驶过程的眼动凝视数据揭示了该特征参数 在驾驶员查看后视镜过程中的累积概率局部峰值分布规律，并提出一种基准特征值实时估算方 法和后视镜查看行为阈值判定原理。实验结果表明，该方法适应于不同脸型，具有良好的抗干 扰能力，综合检测准确率达96.1%。     

Energy optimization for mobile video streaming via an aggregate model

Wireless video streaming on smartphones drains a significantly large fraction of battery energy, which is primarily consumed by wireless network interfaces for downloading unused data and repeatedly switching radio interface. In this paper, we propose an energy-efficient download scheduling algorithm for video streaming based on an aggregate model that utilizes user’s video viewing history to predict user behavior when watching a new video, thereby minimizing wasted energy when streaming over wireless network interfaces. The aggregate model is constructed by a personal retention model with users’ personal viewing history and the audience retention on crowd-sourced viewing history, which can accurately predict the user behavior of watching videos by balancing “user interest” and “video attractiveness”. We evaluate different users streaming multiple videos in various wireless environments and the results illustrate that the aggregate model can help reduce energy waste by 20 % on average. In addition, we also discuss implementation details and extensions, such as dynamically updating personal retention, balancing audience and personal retention, categorizing videos for accurate model.     

Older people’s production and appropriation of digital videos: an ethnographic study

While most of today’s children, young people, and adults are both consumers and producers of digital content, very little is known about older people as digital content creators. Drawing on a three-year ethnographic study, this paper reports on the digital video production and appropriation of approximately 200 older people (aged 60–85). They generated 320 videos over the course of the study. We show their motivations for engaging in digital video production, discuss their planned video making, and highlight their creativity while editing videos. We show the different meanings they ascribed to digital videos in their social appropriation of these objects, the meaningful strategies they adopted to share videos, and the impact on their perceived wellbeing. Furthermore, we outline the solutions the participants developed to overcome or cope with interaction issues they faced over time. We argue that the results portray older people as active and creative makers of digital videos with current video capturing, editing, and sharing technologies. We contend that this portrayal both encourages us to re-consider how older people should be seen within human–computer interaction and helps to frame future research/design activities that bridge the grey digital divide.     

Documenting and sharing software knowledge using screencasts

Screencasts are used to capture a developer’s screen while they narrate how a piece of software works or how the software can be extended. They have recently become a popular alternative to traditional text-based documentation. This paper describes our investigation into how developers produce and share developer-focused screencasts. In this study, we identified and analyzed a set of development screencasts from YouTube to explore what kinds of software knowledge are shared in video walkthroughs of code and what techniques are used for sharing software knowledge. We also interviewed YouTube screencast producers to understand their motivations for creating screencasts as well as to discover the challenges they face while producing code-focused videos. Finally, we compared YouTube screencasts to videos hosted on the professional RailsCasts website to better understand the differences and practices of this more curated ecosystem with the YouTube platform. Our three-phase study showed that video is a useful medium for communicating program knowledge between developers and that developers build their online persona and reputation by sharing videos through social channels. These findings led to a number of best practices for future screencast creators.