Search results

For studies in educational data mining or learning Analytics, the prediction of student’s performance or early warning is one of the most popular research topics. However, research gaps indicate a paucity of research using machine learning and deep learning (DL) models in predictive analytics that include both behaviors and text analysis.

This study combined behavioral data and discussion board content to construct early warning models with machine learning and DL algorithms. In total, 680 course sections, 12,869 students and 14,951,368 logs were collected from a K-12 virtual school in the USA. Three rounds of experiments were conducted to demonstrate the effectiveness of the proposed approach.

The DL model performed better than machine learning models and was able to capture 51% of at-risk students in the eighth week with 86.8% overall accuracy. The combination of behavioral and textual data further improved the model’s performance in both recall and accuracy rates. The total word count is a more general indicator than the textual content feature. Successful students showed more words in analytic, and at-risk students showed more words in authentic when text was imported into a linguistic function word analysis tool. The balanced threshold was 0.315, which can capture up to 59% of at-risk students.

The results of this exploratory study indicate that the use of student behaviors and text in a DL approach may improve the predictive power of identifying at-risk learners early enough in the learning process to allow for interventions that can change the course of their trajectory.

Even though Sri Lanka has established Early Warning (EW) mechanisms and Evacuation Procedures (EP) for the communities affected by the coastal disasters, there are several gaps, which hinder effective mechanisms in operation of disaster management practices. These gaps affect both the vulnerable communities and relevant authorities involved in the Disaster Management sector. This paper aims to identify and evaluate those gaps while providing adequate solutions.

For that, questionnaire surveys were carried out with a sample size of 217 via an online survey (117) among the urban level and interviews and telephone interviews (100) with the village level coastal communities. Data analysis was carried out using statistical analysis of questionnaire surveys and grounded theory was used for in-depth qualitative study.

Primary and secondary data obtained from the surveys were categorized under five themes, namely, response to early warning systems, evacuation routes, shelters, drills and training, effect of having a family vehicle, relatives and domestic animals, evacuation of people with special needs and cooperation with local government units. This paper analyses these themes in detail.

While critically evaluating the gaps in existing early warning mechanisms and evacuation procedures, this paper identifies correlations between some of the gaps and recommendations as well. Input from the international academics were also obtained at different forums and have strengthen the findings to overcome the barriers, which hinder successful mechanisms.

The purpose of the study is to evaluate the severity of public events in real time from the perspective of social media and to construct the early warning mechanism of public events.

This study constructed the severity assessment system of public events from the dimensions of the netizens' role, the Internet media's role, the spread of public events and the attitudes and feelings of netizens. The method of analyzing the influence tendency of the public event severity indicators was proposed. A total of 1,107,308 microblogging entries regarding four public events were investigated. The severity of public events was divided into four levels.

It is found that serious public events have higher indicator values than medium level events on the microblogging platform. A quantitative severity classification standard for public events was established and the early warning mechanism of public events was built.

Microblogging and other social media platforms provide rich clues for the real-time study and judgment of public events. This study only investigated the Weibo platform as the data source. Other social media platforms can also be considered in future.

Different from the ex-post evaluation method of judging the severity of public events based on their physical loss, this study constructed a quantitative method to dynamically determine the severity of public events according to the clues reflected by social media. The results can help the emergency management departments judge the severity of public events objectively and reduce the subjective negligence and misjudgment.

This article aims to summarise two papers from Australia on supporting young people in early intervention for psychosis. Both have implications for young people's social inclusion and the design of early intervention services.

The first paper reports a new analysis of a trial of specialist employment and education support in an early intervention service. It used a statistical method called logistic regression to test whether only employment support predicted 41 participants’ success in getting into employment and education, or whether things like condition severity also mattered. The second paper reports on a new online support package for young people with “first episode psychosis” and how acceptable it was. The authors looked at 20 participants’ use of the package, and examined their well‐being before and after using it.

The first paper reported that nothing except getting specialist employment and education support predicted young people's entry to work or education. They recommend that young people in early intervention should not be denied vocational support because of things like “psychiatric symptoms”. In the second paper, young people in early intervention who used the online package reacted positively. The authors recommend a full controlled trial of the package. It could help young people when leaving the service to maintain their gains.

These papers advance research on early intervention psychosis services regarding young people's social inclusion needs. Specialist vocational support could prevent life‐long social exclusion. An innovative online support package has not yet been proven, but with fast‐evolving technology, it might help future service users stay well when leaving the service.

The purpose of this paper is to use data available through the hybrid (blended online and face to face) learning environment to explore both a direct behavioral measure of conscientiousness and gender in predicting hybrid classroom performance.

Variables measuring both student conscientious behavior, in the hybrid classroom, and gender were examined to determine their relationship to student final grades (i.e. success) in hybrid undergraduate business ethics courses.

The author finds that: first, conscientiousness continues to be a solid predictor of academic success; second, gender continues to be an insignificant predictor of success in the online/hybrid environment; third, using direct behavioral measures of conscientiousness yields results consistent with prior research that linked inventory-based conscientiousness levels to academic performance; and finally, the archiving and data-collection functions of the hybrid classroom represent a rich trove of behavioral data that may be mined for clues to predict student academic success.

As the research is based on data from six hybrid business ethics classrooms at one institution, future research could be extended to different classrooms and different institutions compared across nations. Research implications include highlighting the potential value of using direct measures of conscientiousness to predict performance.

The study sheds light on the tremendous possibilities for conducting applied research on educational performance outcomes using the rich data inherent in the hybrid learning environment. The author has suggested numerous ways to mine the data from the online portion of the hybrid classroom to explore antecedents of academic success. The author suggests that the hybrid classroom can provide data to act as an early warning system for educators to identify struggling students.

The paper builds upon an exploratory study of the use of direct behavioral (rather than inventory self-report) measures of personality in research on educational outcomes as well as introducing avenues for original research on learning behavior based on data afforded by the hybrid educational environment.

The purpose of this paper is to improve the conceptual understanding of the process of participation in early warning systems (EWS) through a review of participatory EWS examples in the academic literature. Specifically, this paper asks: who is involved, what responsibilities do participants hold, what activities are they involved in, and what are the associated successes, issues and outcomes?

A total of 30 cases of participation in EWS documented in the academic literature were identified through online searches. Existing concepts in participation (power and responsibility, communication) and people-centred early warning (risk knowledge, monitoring and warning, communication and dissemination and response capability) were used to examine each paper.

Participation was found to take place through a range of activities across all elements of the EWS. Participation also varied in breadth of inclusion, ranging from the general public to selected volunteers. The majority of cases received support and facilitation from other actors, such as government and NGOs, but the extent of power and responsibility held by participants varied greatly within this. Common successes and issues associated with participatory EWS and the potential outcomes are presented, and the opportunities, challenges and gaps in knowledge are discussed.

This paper links participation and EWS literature to form a clearer conceptualisation of participation in EWS in support of future research in the field. It provides unique insights into who participates, their roles and relations with other actors and the outcomes of participation.

This study aims to explore the dissemination and evolutionary path of online public opinion from a crisis management perspective. By clarifying the influencing factors and dynamic mechanisms of online public opinion dissemination, this study provides insights into attenuating the negative impact of online public opinion and creating a favorable ecological space for online public opinion.

This research employs bibliometric analysis and CiteSpace software to analyze 302 Chinese articles published from 2006 to 2023 in the China National Knowledge Infrastructure (CNKI) database and 276 English articles published from 1994 to 2023 in the Web of Science core set database. Through literature keyword clustering, co-citation analysis and burst terms analysis, this paper summarizes the core scientific research institutions, scholars, hot topics and evolutionary paths of online public opinion crisis management research from both Chinese and international academic communities.

The results show that the study of online public opinion crisis management in China and internationally is centered on the life cycle theory, which integrates knowledge from information, computer and system sciences. Although there are differences in political interaction and stage evolution, the overall evolutionary path is similar, and it develops dynamically in the “benign conflict” between the expansion of the research perspective and the gradual refinement of research granularity.

This study summarizes the research results of online public opinion crisis management from China and the international academic community and identifies current research hotspots and theoretical evolution paths. Future research can focus on deepening the basic theories of public opinion crisis management under the influence of frontier technologies, exploring the subjectivity and emotionality of web users using fine algorithms and promoting the international development of network public opinion crisis management theory through transnational comparison and international cooperation.

The purpose of this chapter is to share the structure and strategies that institutions can use to transform the experience of students learning at a distance. Details on how one of the largest educational systems in the United States, the State University of New York (SUNY), reshaped the student online learning experience via the “Open SUNY” model will be described. Specific strategies for infusing existing models of support with new ways of thinking will be explained.

In particular, this chapter will explore the infrastructure of the Open SUNY model of collaboration, the use of the Open SUNY Institutional Readiness approach for preparing colleges to deliver quality online programming, and the unique Open SUNY+ Signature Element program for assessing the quality of online programming and support structures.

This chapter will also highlight the efforts of one campus, SUNY Canton, to leverage Open SUNY and take its signature element on student engagement to the next level. A case study on Canton will show how the campus incorporated online students in all aspects of campus life to reduce student isolation. Specific online student engagement strategies will be provided.

Compiled by K.G.B. Bakewell covering the following journals published by MCB University Press: Facilities Volumes 8‐18; Journal of Property Investment & Finance Volumes 8‐18; Property Management Volumes 8‐18; Structural Survey Volumes 8‐18.