Multimodal data as a means to understand the learning experience

Most work in the design of learning technology uses click-streams as their primary data source for modelling & predicting learning behaviour. In this paper we set out to quantify what, if any, advantages do physiological sensing techniques provide for the design of learning technologies. We conducted a lab study with 251 game sessions and 17 users focusing on skill development (i.e., user's ability to master complex tasks). We collected click-stream data, as well as eye-tracking, electroencephalography (EEG), video, and wristband data during the experiment. Our analysis shows that traditional click-stream models achieve 39% error rate in predicting learning performance (and 18% when we perform feature selection), while for fused multimodal the error drops up to 6%. Our work highlights the limitations of standalone click-stream models, and quantifies the expected benefits of using a variety of multimodal data coming from physiological sensing. Our findings help shape the future of learning technology research by pointing out the substantial benefits of physiological sensing.     

Writer identification approach based on bag of words with OBI features

Handwriter identification aims to simplify the task of forensic experts by providing them with semi-automated tools in order to enable them to narrow down the search to determine the final identification of an unknown handwritten sample. An identification algorithm aims to produce a list of predicted writers of the unknown handwritten sample ranked in terms of confidence measure metrics for use by the forensic expert will make the final decision.Most existing handwriter identification systems use either statistical or model-based approaches. To further improve the performances this paper proposes to deploy a combination of both approaches using Oriented Basic Image features and the concept of graphemes codebook. To reduce the resulting high dimensionality of the feature vector a Kernel Principal Component Analysis has been used. To gauge the effectiveness of the proposed method a performance analysis, using IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting, has been carried out. The results obtained achieved an accuracy of 96% thus demonstrating its superiority when compared against similar techniques.     

Using LSA and text segmentation to improve automatic Chinese dialogue text summarization

Automatic Chinese text summarization for dialogue style is a relatively new research area. In this paper, Latent Semantic Analysis （LSA） is first used to extract semantic knowledge from a given document, all question paragraphs are identified, an automatic text segmentation approach analogous to Text＇filing is exploited to improve the precision of correlating question paragraphs and answer paragraphs, and finally some ＂important＂ sentences are extracted from the generic content and the question-answer pairs to generate a complete summary. Experimental results showed that our approach is highly efficient and improves significantly the coherence of the summary while not compromising informativeness.     

面向数字人文研究的大规模古籍文本可视化分析与挖掘

传统的古籍开发与应用模式已难以适应人文学科研究的需要,人文学科研究者期待一个技术逻辑和人文逻辑相耦合的数字人文研究范式的出现。本文从古籍文献深层次开发与利用出发,利用新的信息技术与面向数字人文研究跨学科方法,以大规模中国古籍文本为研究对象,采用大数据研究理念,对古籍进行整理、标注、自动分词等处理,以词频分析统计为研究核心,采用数据降噪、基于窗口时间单位的统计分析计算、滑动窗口预测等分析与挖掘方法,采用大数据实时分析技术,实现了实时、在线、立体、可视化、定量分析字词的历史词频分布规律,创建了一个以语言学、历史文献学、历史地理学等人文学科研究为主的古籍实时统计分析平台,可辅助研究者在大量的古籍文献中发现新的模式、现象、趋势等,实现古籍开发与应用模式创新的初步尝试。图11。参考文献36。     

A learning-based method to detect and segment text from scene images

This paper proposes a learning-based method for text detection and text segmentation in natural scene images. First, the input image is decomposed into multiple connected-components (CCs) by Niblack clustering algorithm. Then all the CCs including text CCs and non-text CCs are verified on their text features by a 2-stage classification module, where most non-text CCs are discarded by an attentional cascade classifier and remaining CCs are further verified by an SVM. All the accepted CCs are output to result in text only binary image. Experiments with many images in different scenes showed satisfactory performance of our proposed method.     

The expected value of possession in professional rugby league match-play

This study estimated the expected point value for starting possessions in different field locations during rugby league match-play and calculated the mean expected points for each subsequent play during the possession. It also examined the origin of tries scored according to the method of gaining possession. Play-by-play data were taken from all 768 regular-season National Rugby League (NRL) matches during 2010–2013. A probabilistic model estimated the expected point outcome based on the net difference in points scored by a team in possession in a given situation. An iterative method was used to approximate the value of each situation based on actual scoring outcomes. Possessions commencing close to the opposition’s goal-line had the highest expected point equity, which decreased as the location of the possession moved towards the team’s own goal-line. Possessions following an opposition error, penalty or goal-line dropout had the highest likelihood of a try being scored on the set subsequent to their occurrence. In contrast, possessions that follow an opposition completed set or a restart were least likely to result in a try. The expected point values framework from our model has applications for informing playing strategy and assessing individual and team performance in professional rugby league.     

存在与生成:基于文本接受的教学认识逻辑

文本是客观世界所呈现出的本体存在与应然样态。作为教学的文本具有客观性、接受性与认同性。由于对先验内容的观念体认,召唤结构的内发生成,共生互融的认同语境,使通过文本的教学得以可能。基于文本接受的教学认识逻辑,应回归知识本体,对文本进行由博返约;激发召唤结构,生发基于作品的动态文本;追寻期待视野,涵育共生性的对话交往,从而实现主体与文本的共存。     

衔接理论与大学英语阅读教学

在英语听说读写四大技能中,阅读占有极其重要的地位。提高学生的阅读理解能力,在很大程度上是提高了他们运用所学外语的全部技能。将衔接理论运用于大学英语教学具体实践,可知阅读教学中有意识地运用衔接理论对学生进行阅读策略训练,能够有效地提高阅读理解水平。     

结构分析法在物理教材分析中的运用

介绍了物理教学中的结构分析法的内容及方法,并运用结构分析法对初中物理“力”这一章教材进行了分析与研究。     

Making sense of learner and learning Big Data: reviewing five years of Data Wrangling at the Open University UK

Most distance learning institutions collect vast amounts of learning data. Making sense of this ‘Big Data’ can be a challenge, in particular when data are stored at different data warehouses and require advanced statistical skills to interpret complex patterns of data. As a leading institute on learning analytics, the Open University UK instigated in 2012 a Data Wrangling initiative. This provided every Faculty with a dedicated academic with expertise data analysis and whose task is to provide strategic, pedagogical and sense-making advice to staff and senior management. Given substantial changes within the OU (e.g. new Faculty structure, real-time dashboards, two large-scale adoptions of predictive analytics approaches, increased reliance on analytics), this embedded case study provides an in-depth review of lessons learned of five years of data wrangling. We will elaborate on the design of the new structure, its strengths and potential weaknesses, and affordances to be adopted by other institutions.