Author Profiling (AP), which aims to predict an author's demographics characteristics automatically by using texts written by the author, is an important mechanism for many applications, as well as highly challenging. In this research, we analyse various previous machine learning models for AP, with respect to their potential for our research problem. Based on this, we propose a Deep Learning Architecture to predict the demographics characteristics of the learners in MOOCs, incorporating multi-feature representations and ensemble learning methods. Specifically, we employ a novel pipeline, combining the most successful deep learning classifiers, Convolution Neural Networks, Recurrent Neural Networks and Recursive Neural Networks, to learn from a text. Moreover, beside the state-of-the-art training involving character and word-level input, we additionally propose phrase-level input. With this approach, we aim at deepening our understanding of the writing style of learners, and thus, predict the author profile with high accuracy. In this paper, we propose the model and architecture, and report on initial tests of our model on a large dataset from the FutureLearn platform, to predict the demographics characteristics of the learners.
{"title":"Predicting Learners' Demographics Characteristics: Deep Learning Ensemble Architecture for Learners' Characteristics Prediction in MOOCs","authors":"Tahani Aljohani, A. Cristea","doi":"10.1145/3345094.3345119","DOIUrl":"https://doi.org/10.1145/3345094.3345119","url":null,"abstract":"Author Profiling (AP), which aims to predict an author's demographics characteristics automatically by using texts written by the author, is an important mechanism for many applications, as well as highly challenging. In this research, we analyse various previous machine learning models for AP, with respect to their potential for our research problem. Based on this, we propose a Deep Learning Architecture to predict the demographics characteristics of the learners in MOOCs, incorporating multi-feature representations and ensemble learning methods. Specifically, we employ a novel pipeline, combining the most successful deep learning classifiers, Convolution Neural Networks, Recurrent Neural Networks and Recursive Neural Networks, to learn from a text. Moreover, beside the state-of-the-art training involving character and word-level input, we additionally propose phrase-level input. With this approach, we aim at deepening our understanding of the writing style of learners, and thus, predict the author profile with high accuracy. In this paper, we propose the model and architecture, and report on initial tests of our model on a large dataset from the FutureLearn platform, to predict the demographics characteristics of the learners.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127513105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abnormal signals are extremely important to almost every area including industry, medical and transportation. However, the various huge quantity signals make signal detection applying to every condition a challenging problem. Anomaly detection of time series mainly has three difficulties: time sequence, high dimensionality, no common rules. This paper proposes a novel algorithm for signal detection based on temporal clustering. The algorithm uses convolution layer and Bi-GRU to reduce the dimensionality of time series data and get latent representation. Clustering with latent representation to detect types of abnormal signal can solve the problem effectively. To prove the effectiveness of the algorithm, simulation of the real signal and visualization of the result are also done properly.
{"title":"Abnormal Signal Detection based on Time Series Clustering","authors":"Xiao Zhang, Xinhang Li, Hongyi Li, Di Zhao","doi":"10.1145/3345094.3345109","DOIUrl":"https://doi.org/10.1145/3345094.3345109","url":null,"abstract":"Abnormal signals are extremely important to almost every area including industry, medical and transportation. However, the various huge quantity signals make signal detection applying to every condition a challenging problem. Anomaly detection of time series mainly has three difficulties: time sequence, high dimensionality, no common rules. This paper proposes a novel algorithm for signal detection based on temporal clustering. The algorithm uses convolution layer and Bi-GRU to reduce the dimensionality of time series data and get latent representation. Clustering with latent representation to detect types of abnormal signal can solve the problem effectively. To prove the effectiveness of the algorithm, simulation of the real signal and visualization of the result are also done properly.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124216649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advance of information and communication technology enables us to change the way we live and learn something. The multimodal environment which becomes a strong feature of today's world requires language learner to incorporate more than one mode in the teaching and learning process and therefore the provision of multimodal environments is crucial to be done by language teachers. This study aims to investigate the level of multimodal literacy of pre-service teachers as well as how they instantiate the literacy in their teaching. This study involved 40 students of Pendidikan Profesi Guru (PPG Program) or Professional Teacher Education as the participants. A questionnaire consisting of several statements related to multimodal literacy and semi-structured interviews were used as data collection technique. Conclusions are drawn and suggestions are made for the English education program and further research as well.
{"title":"Exploring EFL Pre-service Teachers' Multimodal Literacy: Level and Implementations","authors":"S. Pramono, D. Suherdi","doi":"10.1145/3345094.3345103","DOIUrl":"https://doi.org/10.1145/3345094.3345103","url":null,"abstract":"The advance of information and communication technology enables us to change the way we live and learn something. The multimodal environment which becomes a strong feature of today's world requires language learner to incorporate more than one mode in the teaching and learning process and therefore the provision of multimodal environments is crucial to be done by language teachers. This study aims to investigate the level of multimodal literacy of pre-service teachers as well as how they instantiate the literacy in their teaching. This study involved 40 students of Pendidikan Profesi Guru (PPG Program) or Professional Teacher Education as the participants. A questionnaire consisting of several statements related to multimodal literacy and semi-structured interviews were used as data collection technique. Conclusions are drawn and suggestions are made for the English education program and further research as well.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123971034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study deals with the effectiveness of social inquiry learning model towards problem-solving skill especially in social studies for fourth-grade primary school in an elementary school in Bandung, West Java Indonesia. This study used a quantitative method with quasi-experimental design by one-shot case study design research. Data was collected by 12 fourth grade at a primary school in Bandung, West Java by a post-test. The topic of learning was about social problems in social studies. Next, the collected data were analyzed using t-test. This data processing used SPSS version 22 program. The final calculation with the t-test is obtained t- value = 12,696. It indicates that H1 is accepted and H0 is rejected. Therefore, H1 indicates that social inquiry learning model is effective towards social problem-solving skill. The social inquiry learning model does not only require students to actively master the cognitive aspects but also can develop some aspects of skills and attitudes such as developing a sense of responsibility and creativity in solving problems rationally.
本研究以印尼西爪哇万隆一小学四年级学生为研究对象，探讨社会探究学习模式对学生解决问题能力，尤其是社会研究的效果。本研究采用准实验设计的定量方法，采用单次案例研究设计研究。数据由西爪哇万隆一所小学的12名四年级学生通过后测收集。学习的主题是关于社会研究中的社会问题。接下来，对收集到的数据进行t检验。本数据处理使用SPSS 22版程序。最后用t检验计算得到t- value = 12696。表示接受H1，拒绝H0。因此，H1表明社会探究学习模式对社会问题解决技能是有效的。社会探究学习模式不仅要求学生主动掌握认知方面的知识，还可以培养学生理性解决问题的责任感、创造性等方面的技能和态度。
{"title":"Effectiveness Social Inquiry Learning Model towards Students' Problem-Solving Skill in a Primary School","authors":"S. Nurlaili, Sapriya","doi":"10.1145/3345094.3345106","DOIUrl":"https://doi.org/10.1145/3345094.3345106","url":null,"abstract":"This study deals with the effectiveness of social inquiry learning model towards problem-solving skill especially in social studies for fourth-grade primary school in an elementary school in Bandung, West Java Indonesia. This study used a quantitative method with quasi-experimental design by one-shot case study design research. Data was collected by 12 fourth grade at a primary school in Bandung, West Java by a post-test. The topic of learning was about social problems in social studies. Next, the collected data were analyzed using t-test. This data processing used SPSS version 22 program. The final calculation with the t-test is obtained t- value = 12,696. It indicates that H1 is accepted and H0 is rejected. Therefore, H1 indicates that social inquiry learning model is effective towards social problem-solving skill. The social inquiry learning model does not only require students to actively master the cognitive aspects but also can develop some aspects of skills and attitudes such as developing a sense of responsibility and creativity in solving problems rationally.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114260832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study investigates the relationship the courses achievement of undergraduate students in Informatics Mathematics curriculum. Social Network Analysis and Pearson product Moment Correlation Coefficient are used to determine which courses are significant important and influence predictors. Data collected is from the sample of 91 online report submitted by science graduated students who have graduated during the academic year 2010-2017. The results of the study indicate that Linear Algebra and Discrete Mathematics are the highest score of weighted degree centrality as Mathematics information technology is the highest score of betweenness centrality and English for informatics Mathematics influence over the whole courses.
{"title":"Applying Social Network Analysis on Courses relationship in Informatics Mathematics Curriculum","authors":"K. Bussaban, Asekha Khantavchai","doi":"10.1145/3345094.3345115","DOIUrl":"https://doi.org/10.1145/3345094.3345115","url":null,"abstract":"This study investigates the relationship the courses achievement of undergraduate students in Informatics Mathematics curriculum. Social Network Analysis and Pearson product Moment Correlation Coefficient are used to determine which courses are significant important and influence predictors. Data collected is from the sample of 91 online report submitted by science graduated students who have graduated during the academic year 2010-2017. The results of the study indicate that Linear Algebra and Discrete Mathematics are the highest score of weighted degree centrality as Mathematics information technology is the highest score of betweenness centrality and English for informatics Mathematics influence over the whole courses.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127602026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Science, Technology, Engineering, and Mathematics (STEM) education is gaining more attention not today but has been under research, and discussion for the past few decades. Factors that are considered for research include but not limited to the following, culture on campus, teaching and learning models, and student experience in classroom, gender bias, and stereotypes. One of the major factors is the teaching model adopted which have impact on the student learning styles and their experience in the classroom. Teaching models include traditional models, modern flipped class-room models, and active learning approaches. This study focuses on active learning approaches and their impact on students learning and experience. Light-weight team is an active learning approach, in which team members have little direct impact on each other's final grades, with significant long-term socialization. In this work we used data from end of course student evaluation. We propose extend our previous method for assessing the effectiveness of the Light-weight team teaching model, through automatic detection of emotions in student feedback in computer science course by creating multi-label for each text comment. The students are surveyed about their feelings and thoughts about teaching and learning models adopted and student experience in the classroom. Results show that implementation of these methods result in increased positivity in student emotions.
{"title":"Multi-Label Emotion Mining From Student Comments","authors":"A. Tzacheva, Jaishree Ranganathan, R. Jadi","doi":"10.1145/3345094.3345112","DOIUrl":"https://doi.org/10.1145/3345094.3345112","url":null,"abstract":"Science, Technology, Engineering, and Mathematics (STEM) education is gaining more attention not today but has been under research, and discussion for the past few decades. Factors that are considered for research include but not limited to the following, culture on campus, teaching and learning models, and student experience in classroom, gender bias, and stereotypes. One of the major factors is the teaching model adopted which have impact on the student learning styles and their experience in the classroom. Teaching models include traditional models, modern flipped class-room models, and active learning approaches. This study focuses on active learning approaches and their impact on students learning and experience. Light-weight team is an active learning approach, in which team members have little direct impact on each other's final grades, with significant long-term socialization. In this work we used data from end of course student evaluation. We propose extend our previous method for assessing the effectiveness of the Light-weight team teaching model, through automatic detection of emotions in student feedback in computer science course by creating multi-label for each text comment. The students are surveyed about their feelings and thoughts about teaching and learning models adopted and student experience in the classroom. Results show that implementation of these methods result in increased positivity in student emotions.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126552389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents an overview of the development of CALL research in the past 11 years (2007-2018). Based on the previous studies published in the most influential eight foreign language teaching journals in China, a statistical analysis is made on the collected research and features and tendencies of CALL research are explored and summarized based on the comparison results of Na Min's research(which also gives a statistical analysis on CALL research published in 1995-2006 with the same collected range).The paper concludes that the past seven years sees a sharp drop of research in CALL. With respect to research areas, the following five are identified: the theoretical discussions relevant to CALL, the classroom practice of CALL, the positioning of teachers and students in CALL, the computer-assisted language testing and the development of computer technologies and software. Finally, the conclusions along with some suggestions for further improvements are raised.
{"title":"Statistical Analysis and Introspection on Research Situation of Foreign Language Teaching in China under CALL Environment","authors":"Zhenmei Shi, Yifei Luan","doi":"10.1145/3345094.3345117","DOIUrl":"https://doi.org/10.1145/3345094.3345117","url":null,"abstract":"This paper presents an overview of the development of CALL research in the past 11 years (2007-2018). Based on the previous studies published in the most influential eight foreign language teaching journals in China, a statistical analysis is made on the collected research and features and tendencies of CALL research are explored and summarized based on the comparison results of Na Min's research(which also gives a statistical analysis on CALL research published in 1995-2006 with the same collected range).The paper concludes that the past seven years sees a sharp drop of research in CALL. With respect to research areas, the following five are identified: the theoretical discussions relevant to CALL, the classroom practice of CALL, the positioning of teachers and students in CALL, the computer-assisted language testing and the development of computer technologies and software. Finally, the conclusions along with some suggestions for further improvements are raised.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"326 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134416232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper offers an alternative to teach recount text grounded on systemic functional linguistics. Firstly, by employing qualitative study case design in purposing to unravel the specific phenomena based on the participants' perspective (Creswell, 1994), specifically by analysing students' writing below SFL perspective, it was found that students in Grade VIII Junior High School Ciparay encounter some problems in writing narrative text such as tense, the use of more than one process and finites, the absence of object or recipient, and the absence of themes. After discovering those analysed problem, this paper tried to to use a strategy called TAD (Transitions, Actions, Details). It is hoped that this strategy will improve students, ability in writing recount text.
{"title":"Unravel Students' Problems in Writing Recount Text: Below SFL Belt and TAD Strategy","authors":"D. Oktaviani","doi":"10.1145/3345094.3345116","DOIUrl":"https://doi.org/10.1145/3345094.3345116","url":null,"abstract":"This paper offers an alternative to teach recount text grounded on systemic functional linguistics. Firstly, by employing qualitative study case design in purposing to unravel the specific phenomena based on the participants' perspective (Creswell, 1994), specifically by analysing students' writing below SFL perspective, it was found that students in Grade VIII Junior High School Ciparay encounter some problems in writing narrative text such as tense, the use of more than one process and finites, the absence of object or recipient, and the absence of themes. After discovering those analysed problem, this paper tried to to use a strategy called TAD (Transitions, Actions, Details). It is hoped that this strategy will improve students, ability in writing recount text.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"119 46","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120820657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper shows the results of a project carried out in 2018 by a group of professors from the School of Mathematics of the Costa Rica Institute of Technology (ITCR). The main objective of the project was to encourage parents and any person responsible for the student, to develop a good attitude towards the mathematics, its usefulness and importance; and to provide them with tools that they could use to help the students in their academic tasks. This project was carried out in six elementary schools of the central district of Cartago, Costa Rica and partially consisted in teaching two workshops of two hours each in all the selected schools. These workshops focused on the acquisition of didactic skills to support the academic tasks of their children, specifically in the subjects of fractions and basic math operations.
{"title":"Family involvement and guidance in taking an active role in the process of teaching and learning mathematics: a case study from Costa Rica","authors":"Zuleyka Suárez-Valdés-Ayala, Rebeca Solis-Ortega, Angie Solís-Palma","doi":"10.1145/3345094.3345096","DOIUrl":"https://doi.org/10.1145/3345094.3345096","url":null,"abstract":"This paper shows the results of a project carried out in 2018 by a group of professors from the School of Mathematics of the Costa Rica Institute of Technology (ITCR). The main objective of the project was to encourage parents and any person responsible for the student, to develop a good attitude towards the mathematics, its usefulness and importance; and to provide them with tools that they could use to help the students in their academic tasks. This project was carried out in six elementary schools of the central district of Cartago, Costa Rica and partially consisted in teaching two workshops of two hours each in all the selected schools. These workshops focused on the acquisition of didactic skills to support the academic tasks of their children, specifically in the subjects of fractions and basic math operations.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116733724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A lab experiment to illustrate major concepts of artificial intelligence is proposed. For this, a condition monitoring application using a Raspberry Pi and Simulink is developed for a simple mechatronic system. The experiment is described in detail, example results are shown and the students' overall positive evaluation of the experiment is given.
{"title":"Developing a Condition Monitoring System as an Artificial Intelligence Lab Experiment","authors":"S. Matzka, A. Franke","doi":"10.1145/3345094.3345110","DOIUrl":"https://doi.org/10.1145/3345094.3345110","url":null,"abstract":"A lab experiment to illustrate major concepts of artificial intelligence is proposed. For this, a condition monitoring application using a Raspberry Pi and Simulink is developed for a simple mechatronic system. The experiment is described in detail, example results are shown and the students' overall positive evaluation of the experiment is given.","PeriodicalId":160662,"journal":{"name":"Proceedings of the 4th International Conference on Information and Education Innovations","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134126467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：