Prediction of student attrition risk using machine learning

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mauricio Barramuño ◽  
Claudia Meza-Narváez ◽  
Germán Gálvez-García
Keyword(s):  
Machine Learning ◽  
Student Retention ◽  
Quantitative Research ◽  
Student Attrition ◽  
Supervised Machine Learning ◽  
Computer Tool ◽  
Content Type ◽  
Academic Management ◽  
Qualitative Variables ◽  
The University

PurposeThe prediction of student attrition is critical to facilitate retention mechanisms. This study aims to focus on implementing a method to predict student attrition in the upper years of a physiotherapy program.Design/methodology/approachMachine learning is a computer tool that can recognize patterns and generate predictive models. Using a quantitative research methodology, a database of 336 university students in their upper-year courses was accessed. The participant's data were collected from the Financial Academic Management and Administration System and a platform of Universidad Autónoma de Chile. Five quantitative and 11 qualitative variables were chosen, associated with university student attrition. With this database, 23 classifiers were tested based on supervised machine learning.FindingsAbout 23.58% of males and 17.39% of females were among the attrition student group. The mean accuracy of the classifiers increased based on the number of variables used for the training. The best accuracy level was obtained using the “Subspace KNN” algorithm (86.3%). The classifier “RUSboosted trees” yielded the lowest number of false negatives and the higher sensitivity of the algorithms used (78%) as well as a specificity of 86%.Practical implicationsThis predictive method identifies attrition students in the university program and could be used to improve student retention in higher grades.Originality/valueThe study has developed a novel predictive model of student attrition from upper-year courses, useful for unbalanced databases with a lower number of attrition students.

Evaluating disaster-related tweet credibility using content-based and user-based features

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Nasser Assery ◽  
Yuan (Dorothy) Xiaohong ◽  
Qu Xiuli ◽  
Roy Kaushik ◽  
Sultan Almalki
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Emergency Response ◽  
Learning Model ◽  
Performance Comparison ◽  
Supervised Machine Learning ◽  
Learning Methods ◽  
Content Type ◽  
Machine Learning Classification

Purpose This study aims to propose an unsupervised learning model to evaluate the credibility of disaster-related Twitter data and present a performance comparison with commonly used supervised machine learning models. Design/methodology/approach First historical tweets on two recent hurricane events are collected via Twitter API. Then a credibility scoring system is implemented in which the tweet features are analyzed to give a credibility score and credibility label to the tweet. After that, supervised machine learning classification is implemented using various classification algorithms and their performances are compared. Findings The proposed unsupervised learning model could enhance the emergency response by providing a fast way to determine the credibility of disaster-related tweets. Additionally, the comparison of the supervised classification models reveals that the Random Forest classifier performs significantly better than the SVM and Logistic Regression classifiers in classifying the credibility of disaster-related tweets. Originality/value In this paper, an unsupervised 10-point scoring model is proposed to evaluate the tweets’ credibility based on the user-based and content-based features. This technique could be used to evaluate the credibility of disaster-related tweets on future hurricanes and would have the potential to enhance emergency response during critical events. The comparative study of different supervised learning methods has revealed effective supervised learning methods for evaluating the credibility of Tweeter data.

Thermal comfort prediction by applying supervised machine learning in green sidewalks of Tehran

2020 ◽  
Vol 9 (4) ◽  
pp. 361-374
Author(s):  
Nasim Eslamirad ◽  
Soheil Malekpour Kolbadinejad ◽  
Mohammadjavad Mahdavinejad ◽  
Mohammad Mehranrad
Keyword(s):  
Machine Learning ◽  
Thermal Comfort ◽  
Urban Design ◽  
Energy Modeling ◽  
Supervised Machine Learning ◽  
Outdoor Thermal Comfort ◽  
Social Implications ◽  
Design Strategies ◽  
Content Type ◽  
The Future

PurposeThis research aims to introduce a new methodology for integration between urban design strategies and supervised machine learning (SML) method – by applying both energy engineering modeling (evaluating phase) for the existing green sidewalks and statistical energy modeling (predicting phase) for the new ones – to offer algorithms that help to catch the optimum morphology of green sidewalks, in case of high quality of the outdoor thermal comfort and less errors in results.Design/methodology/approachThe tools of the study are the way of processing by SML, predicting the future based on the past. Machine learning is benefited from Python advantages. The structure of the study consisted of two main parts, as the majority of the similar studies follow: engineering energy modeling and statistical energy modeling. According to the concept of the study, at first, from 2268 models, some are randomly selected, simulated and sensitively analyzed by ENVI-met. Furthermore, the Envi-met output as the quantity of thermal comfort – predicted mean vote (PMV) and weather items are inputs of Python. Then, the formed data set is processed by SML, to reach the final reliable predicted output.FindingsThe process of SML leads the study to find thermal comfort of current models and other similar sidewalks. The results are evaluated by both PMV mathematical model and SML error evaluation functions. The results confirm that the average of the occurred error is about 1%. Then the method of study is reliable to apply in the variety of similar fields. Finding of this study can be helpful in perspective of the sustainable architecture strategies in the buildings and urban scales, to determine, monitor and control energy-based behaviors (thermal comfort, heating, cooling, lighting and ventilation) in operational phase of the systems (existed elements in buildings, and constructions) and the planning and designing phase of the future built cases – all over their life spans.Research limitations/implicationsLimitations of the study are related to the study variables and alternatives that are notable impact on the findings. Furthermore, the most trustable input data will result in the more accuracy in output. Then modeling and simulation processes are most significant part of the research to reach the exact results in the final step.Practical implicationsFinding of the study can be helpful in urban design strategies. By finding outdoor thermal comfort that resulted from machine learning method, urban and landscape designers, policymakers and architects are able to estimate the features of their designs in air quality and urban health and can be sure in catching design goals in case of thermal comfort in urban atmosphere.Social implicationsBy 2030, cities are delved as living spaces for about three out of five people. As green infrastructures influence in moderating the cities’ climate, the relationship between green spaces and habitants’ thermal comfort is deduced. Although the strategies to outside thermal comfort improvement, by design methods and applicants, are not new subject to discuss, applying machines that may be common in predicting results can be called as a new insight in applying more effective design strategies and in urban environment’s comfort preparation. Then study’s footprint in social implications stems in learning from the previous projects and developing more efficient strategies to prepare cities as the more comfortable and healthy places to live, with the more efficient models and consuming money and time.Originality/valueThe study achievements are expected to be applied not only in Tehran but also in other climate zones as the pattern in more eco-city design strategies. Although some similar studies are done in different majors, the concept of study is new vision in urban studies.

Using energy profiles to identify university energy reduction opportunities

2016 ◽  
Vol 17 (2) ◽  
pp. 188-207 ◽  
Author(s):  
Nandarani Maistry ◽  
Harold Annegarn
Keyword(s):  
South Africa ◽  
Energy Efficiency ◽  
Energy Consumption ◽  
Quantitative Research ◽  
Electricity Consumption ◽  
Working Hours ◽  
Content Type ◽  
Academic Calendar ◽  
The University

Purpose – The purpose of this paper is to outline efforts at the University of Johannesburg, a large metropolitan university in Gauteng province, to examine energy efficiency within the context of the green campus movement, through the analysis of electricity consumption patterns. The study is particularly relevant in light of the cumulative 230 per cent increase in electricity costs between 2008 and 2014 in South Africa that has forced institutions of higher education to seek ways to reduce energy consumption. Design/Methodology/Approach – A quantitative research design was adopted for the analysis of municipal electricity consumption records using a case study approach to identify trends and patterns in consumption. The largest campus of the University of Johannesburg, which is currently one of the largest residential universities in South Africa, was selected as a case study. Average diurnal consumption profiles were plotted according to phases of the academic calendar, distinguished by specific periods of active teaching and research (in-session); study breaks, examinations and administration (out-of-session); and recesses. Average profiles per phase of the academic calendar were constructed from the hourly electricity consumption and power records using ExcelTM pivot tables and charts. Findings – It was found that the academic calendar has profound effects on energy consumption by controlling the level of activity. Diurnal maximum consumption corresponds to core working hours, peaking at an average of 2,500 kWh during “in-session” periods, 2,250 kWh during “out-of-session” periods and 2,100 kWh during recess. A high base load was evident throughout the year (between 1,300 and 1,650 kWh), mainly attributed to heating and cooling. By switching off the 350 kW chiller plant on weekdays, a 9 per cent electricity reduction could be achieved during out-of-session and recess periods. Similarly, during in-session periods, a 6 per cent reduction could be achieved. Practical implications – Key strategies and recommendations are presented to stimulate energy efficiency implementation within the institution. Originality Value – Coding of consumption profiles against the academic calendar has not been previously done in relation to an academic institution. The profiles were used to establish the influence of the academic calendar on electricity consumption, which along with our own observation were used to identify specific consumption reduction opportunities worth pursuing.

Examples of Academic Support Systems to Improve Student Success

2006 ◽  
Author(s):  
Amir Karimi
Keyword(s):  
Student Success ◽  
Student Retention ◽  
Support Systems ◽  
San Antonio ◽  
Academic Support ◽  
Student Attrition ◽  
University Of Texas ◽  
Student Demographics ◽  
Underlying Causes ◽  
The University

The University of Texas at San Antonio (UTSA) has implemented a number of academic support systems to address obstacles to student success and to improve student retention. This paper describes the student demographics at UTSA, provides tracking data on student enrollment and retention, and includes discussion of the underlying causes of student attrition. It will describe some of the programs that are implemented to improve student success. Data is provided to measure the level of success of some of the programs that have implemented for the student success.

scholarly journals Evolution of corporate reputation during an evolving controversy

2019 ◽  
Vol 23 (1) ◽  
pp. 52-71 ◽  
Author(s):  
Siyoung Chung ◽  
Mark Chong ◽  
Jie Sheng Chua ◽  
Jin Cheon Na
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Corporate Reputation ◽  
Supervised Machine Learning ◽  
Future Research ◽  
Content Type ◽  
Twitter Users ◽  
Corporate Crisis ◽  
The Impact

PurposeThe purpose of this paper is to investigate the evolution of online sentiments toward a company (i.e. Chipotle) during a crisis, and the effects of corporate apology on those sentiments.Design/methodology/approachUsing a very large data set of tweets (i.e. over 2.6m) about Company A’s food poisoning case (2015–2016). This case was selected because it is widely known, drew attention from various stakeholders and had many dynamics (e.g. multiple outbreaks, and across different locations). This study employed a supervised machine learning approach. Its sentiment polarity classification and relevance classification consisted of five steps: sampling, labeling, tokenization, augmentation of semantic representation, and the training of supervised classifiers for relevance and sentiment prediction.FindingsThe findings show that: the overall sentiment of tweets specific to the crisis was neutral; promotions and marketing communication may not be effective in converting negative sentiments to positive sentiments; a corporate crisis drew public attention and sparked public discussion on social media; while corporate apologies had a positive effect on sentiments, the effect did not last long, as the apologies did not remove public concerns about food safety; and some Twitter users exerted a significant influence on online sentiments through their popular tweets, which were heavily retweeted among Twitter users.Research limitations/implicationsEven with multiple training sessions and the use of a voting procedure (i.e. when there was a discrepancy in the coding of a tweet), there were some tweets that could not be accurately coded for sentiment. Aspect-based sentiment analysis and deep learning algorithms can be used to address this limitation in future research. This analysis of the impact of Chipotle’s apologies on sentiment did not test for a direct relationship. Future research could use manual coding to include only specific responses to the corporate apology. There was a delay between the time social media users received the news and the time they responded to it. Time delay poses a challenge to the sentiment analysis of Twitter data, as it is difficult to interpret which peak corresponds with which incident/s. This study focused solely on Twitter, which is just one of several social media sites that had content about the crisis.Practical implicationsFirst, companies should use social media as official corporate news channels and frequently update them with any developments about the crisis, and use them proactively. Second, companies in crisis should refrain from marketing efforts. Instead, they should focus on resolving the issue at hand and not attempt to regain a favorable relationship with stakeholders right away. Third, companies can leverage video, images and humor, as well as individuals with large online social networks to increase the reach and diffusion of their messages.Originality/valueThis study is among the first to empirically investigate the dynamics of corporate reputation as it evolves during a crisis as well as the effects of corporate apology on online sentiments. It is also one of the few studies that employs sentiment analysis using a supervised machine learning method in the area of corporate reputation and communication management. In addition, it offers valuable insights to both researchers and practitioners who wish to utilize big data to understand the online perceptions and behaviors of stakeholders during a corporate crisis.

Use of electronic resources by law academics: a case study from the University of Namibia

2020 ◽  
Vol 39 (3) ◽  
pp. 57-68
Author(s):  
Anna Leonard ◽  
Nampa Meameno Hamutumwa ◽  
Chiku Mnubi-Mchombu
Keyword(s):  
Quantitative Research ◽  
Academic Staff ◽  
Sampling Technique ◽  
Structured Interview ◽  
Electronic Resources ◽  
Content Type ◽  
Quantitative Research Methods ◽  
Interview Guide ◽  
The University

Purpose The purpose of this paper is to examine the use of e-resources by the Faculty of Law’s academic staff at the University of Namibia’s (UNAM’s) main campus. The study aimed to determine their level of awareness of electronic resources (e-resources) available to them, how useful and effective they found these e-resources, and the challenges they face in accessing them. Design/methodology/approach A convenient sampling technique was used to select a sample of 12 law academics from the population of 17. The study used both qualitative and quantitative research methods using questionnaires and a semi-structured interview guide. Findings Findings revealed that the majority of the law academics were aware of the e-resources subscribed by UNAM’s library, although some were not aware of the newly subscribed international law databases. The findings further revealed that the academics used e-resources for research, publications and teaching purposes, but irregular training, bandwidth problems and limited searching skills hindered their use of e-resources. Practical implications Findings could be used to inform future collection-development decisions, realignment of information-literacy training and promotion and marketing of library services. Originality/value This study has made a significant contribution in the understanding the use of electronic legal resources by law academics at UNAM. The findings and recommendations could also benefit similar academic institutions in developing countries like Namibia.

Lonely, homesick and struggling: undergraduate students and intention to quit university

2020 ◽  
Vol 28 (4) ◽  
pp. 239-253
Author(s):  
Clive Boddy
Keyword(s):  
Student Retention ◽  
Undergraduate Students ◽  
Social Desirability ◽  
Student Attrition ◽  
Dropping Out ◽  
First Year Students ◽  
Content Type ◽  
Projective Technique ◽  
Thematic Apperception ◽  
Retention And Attrition

Purpose This paper outlines a variety of the research on student attrition and recognises some of the sensitivities that may be involved for some students in dealing with dropping out of university. This paper claims that because of these sensibilities, some student’s responses to direct questions about the reasons for attrition may be biased by social desirability. The purpose of this paper is to get beyond social desirability bias to examine a fuller range of reasons for student retention and attrition. Design/methodology/approach In an exploratory investigation, this research study uses a projective technique which helps to circumvent the conscious defences of respondents. The projective technique is based on the “thematic apperception test” and uses a “bubble drawing” to elicit emotional and more socially undesirable responses. Findings All first-year students appear to consider leaving university, and emotional considerations involving loneliness and homesickness are much more prominent than most quantitative studies acknowledge. For example, in this research, social concerns are twice as prominent as financial concerns, whereas in past survey research, financial concerns have been identified as most prominent. Practical implications To retain students, universities need to provide new students with real care and support, especially in their first few weeks at university. To study retention comprehensively, researchers need to go beyond the confines of positivist research. Originality/value This is the first study that uses a projective technique to investigate student retention and attrition. By going beyond a merely positivist approach to research, a fuller, deeper and more complete understanding of the wide extent and profound nature of the emotional issues involved in student attrition and retention is gained.

Predicting meeting participants’ note-taking from previously uttered dialogue acts

2016 ◽  
Vol 18 (2) ◽  
pp. 170-185
Author(s):  
Antje Bothin ◽  
Paul Clough
Keyword(s):  
Machine Learning ◽  
Information Systems ◽  
Speech Acts ◽  
Information Needs ◽  
Supervised Machine Learning ◽  
Social Implications ◽  
Note Taking ◽  
Content Type ◽  
Similar Work ◽  
Dialogue Acts

Purpose The purpose of this paper is to describe a new supervised machine learning study on the prediction of meeting participant’s personal note-taking from spoken dialogue acts uttered shortly before writing. Design/methodology/approach This novel approach of providing cues for finding important meeting events that would be worth recording in a meeting summary looks at temporal overlaps of multiple people’s note-taking. This research uses data of 124 meetings taken from the AMI meeting corpus. Findings The results show that several machine learning methods that the authors compared were able to classify the data significantly better than a random approach. The best model, decision trees with feature selection, achieved 70 per cent accuracy for the binary distinction writing for any number of participants simultaneously or no writing, whereas the performance for a more fine-grained distinction of the number of participants taking notes showed only about 30 per cent accuracy. Research limitations/implications The findings suggest that meeting participants take personal notes in accordance with the utterance of previously uttered speech acts, particularly dialogue acts about disfluencies and assessments appear to influence the note-taking activities. However, further research is necessary to examine other domains and to determine in what way this behaviour is helpful as a feature source for automatic meeting summarisation, which is useful for more efficiently satisfying people’s information needs about meeting contents. Practical implications The reader of an Information Systems (IS) journal would be interested in this paper because the work described and the findings gained could lead to the development of novel information systems that facilitate the work for businesses and individuals. Innovative meeting capture and retrieval applications, satisfying automatic summaries of important meeting points and sophisticated note-taking tools that suggest content automatically could make people’s daily lives more convenient in the future. Social implications There are wider implications in terms of productivity and efficiency. Business value is increased for the organisation, as human knowledge is built more or less automatically. There are also cognitive and social implications for individuals and possibly an impact on the society as a whole. It is also important for globalisation, social media and mobile devices. Originality/value The topic is new and original, as there has not been much research on it yet. Similar work was carried out recently (Murray, 2015; Bothin and Clough 2014). This is why it is relevant to an IS journal and interesting for the reader. In particular, dialogue acts about disfluencies and assessments appear to influence the note-taking activities. This behaviour is helpful as a feature source for automatic meeting summarisation, which is useful for more efficiently satisfying people’s information needs about meeting contents.

The functions of the National Archives of South Africa regarding universities’ records and archives

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Nkholedzeni Sidney Netshakhuma
Keyword(s):  
South Africa ◽  
Quantitative Research ◽  
Best Practice ◽  
Comparative Case Study ◽  
The South ◽  
Content Type ◽  
National Archives ◽  
Definition Of ◽  
Teaching Learning ◽  
The University

Purpose This paper aims to assess the functions of the National Archives of South Africa regarding universities’ records and archives by comparing the University of the Witwatersrand (Wits) and the University of Venda’s (Univen) implementation of the National Archives and Records Service of South Africa Act, No. 43 of 1996 (NARSSA) provisions 11 and 13, with the view of recommending best practice. Design/methodology/approach The quantitative research methodology was adopted. The data collection tool was a questionnaire completed by 34 heads of divisions, departments and units from the Wits and Univen, supplemented by a document review. Thus, the study population comprised universities’ heads of divisions, departments and units. Findings The National Archives of South Africa is not playing a role in providing advice to universities on how to manage their records and archives to fulfil their teaching, learning and research mandate, protect them from litigation and preserve their corporate memory such as records with national and international significance. Most of the respondents were not aware of the NARSSA provision 11 on the custody and preservation of records, and provision 13 on the management of public records. NARSSA lacks provision specifically for the management of university records. NARSSA appears vague about the management of university records, as it does not explain the legal definition of university records. Research limitations/implications This is a comparative case study limited to Wits and Univen. The shortcoming of this study is that the author did not provide relevant and detailed information for the article reader to fully understand the functions of the NARSSA provisions 11 and 13 regarding university records and archives at Wits and Univen, respectively. Practical implications The study recommends the South Africa legislature to review the NARSSA regarding records and archives’ role in the university. The researcher’s view is that reviewing existing NARSSA provisions 11 and 13 would provide universities with the responsibility of managing some of their national and international records. This might improve the management of records and this, in turn, would enhance the preservation of records. Originality/value This paper appears to be the first to review the functions of the National Archives of South Africa regarding the South African university’s records and archives.

Teachers' perspectives on factors of female students' outperformance and male students' underperformance in higher education

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Muhammad Shoaib ◽  
Hazir Ullah
Keyword(s):  
Higher Education ◽  
Academic Performance ◽  
Quantitative Research ◽  
Male Students ◽  
Primary Data ◽  
Ann Model ◽  
Contributing Factors ◽  
Content Type ◽  
Quantitative Research Methods ◽  
The University

PurposeThis paper attempts to explore possible contributing factors of females' outperformance and males' underperformance in the higher education in Pakistan from teachers' perspective. The central question of the study is what are the key factors that affect female and male students' educational performance at the university level? Using Artificial Neural Network (ANN) as a framework, we attempted to predict differentials of the perceived “female outperformance” and “male underperformance” in higher education. We carried out the study by employing quantitative research methods.Design/methodology/approachThe data for the study come from 253 teachers from University of the Punjab-largest and oldest University in Pakistan. We used a structured questionnaire for data collection. The analysis was carried out with the help of ANN model. Statistical Package for Social Sciences (SPSS) was used to analyze the data.FindingsThe testing results of ANN indicated 85.3% of teachers' perception was correctly predicted on various dimensions of performance differentials across female and male students in higher education.Research limitations/implicationsThe study banks on primary data collected from teachers of the University of University of the Punjab, Pakistan. Thus, the study's universe was limited to one university – University of Punjab. It is purely based on a quantitative approach employing ANN.Practical implicationsThe findings of this study have several significant implications, i.e. it makes a significant contribution to the existing body of scholarly texts on the issue of gender reverse change in academic performance in higher education.Originality/valueThe findings of this research, derived from primary data in Pakistan context, qualify this research as an original one. We also claim that this study is one of the first studies on gender reverse change in academic performance among graduate students in a public sector university of Pakistan employing ANN.

Sign in / Sign up

Export Citation Format

Share Document