Search Results
advancement is worse than that of the Roma men; their main tasks in their traditional communities are still restricted to supplying the family and childbearing; that is one of the important reasons for them to drop out of the school system sooner than their
-based methodologies continues to perplex both researchers and clinicians ( Lilienfeld, Ritschel, Lynn, Cautin, & Latzman, 2013 ). These evidence-based treatments for PTSD, like many treatments, are not free of shortcomings, however. Drop-out rates average 14–16% and
educational institution. In contrast to dropping out, persistence has a positive meaning ( Simpson, 2003 ). Dropout is always a negative outcome, suggesting that the student interrupts his/her studies and leaves the higher education institution without
Oktatási reform hatékonyságának vizsgálata – Tantárgyak nehézségi elemzése IRT-modell segítségével programtervező informatikus hallgatók körében
The effectiveness of education reform – Applying the Rasch model to analyse computer science students' dropout
. , & Salguero , A. ( 2009 ). Factors influencing university drop out rates . Computers & Education , 53 ( 3 ), 563 – 574 . https://doi.org/10.1016/j.compedu.2009
Lemorzsolódás előrejelzése személyre szabott értelmezhető gépi tanulási módszerek segítségével
Predicting dropout using personalized interpretable machine learning tools
Összefoglalás.
A hallgatói lemorzsolódás az egyik legégetőbb probléma a felsőoktatásban. Ebben a munkában a lemorzsolódás előrejelzésén keresztül bemutatjuk, hogyan tudják segíteni a felsőoktatás résztvevőit a magyarázható mesterséges intelligencia (XAI) eszközök, mint például a permutációs fontosság, a parciális függőségi ábra és a SHAP. Végül pedig kitérünk a kutatás gyakorlati hasznosulásának lehetőségeire, például, hogy az egyéni előrejelzések magyarázata hogyan teszi lehetővé a személyre szabott beavatkozást. Az elemzések során azt találtuk, hogy a középiskolai tanulmányi átlag bír a legnagyobb prediktív erővel a végzés tényére vonatkozóan. Továbbá annak ellenére, hogy egy műszaki egyetem adatait elemeztük, azt találtuk, hogy a humán tárgyaknak is nagy inkrementális prediktív erejük van a végzés tényére vonatkozóan a reál tárgyakhoz képest.
Summary.
Delayed completion and student drop-out are some of the most critical problems in higher education, especially regarding STEM programs. A high drop-out rate induces both individual and economic loss, hence a detailed investigation of the main reasons for dropping out is warranted. Recently, there has been a lot of interest in the use of machine learning methods for the early detection of students at risk of dropping out. However, there has not been much debate on the use of interpretable machine learning (IML) and explainable artificial intelligence (XAI) technologies for dropout prediction. In this paper, we show how IML and XAI techniques can assist educational stakeholders in dropout prediction using data from the Budapest University of Technology and Economics. We demonstrate that complex black-box machine learning algorithms, for example CatBoost, are able to effectively detect at-risk student using only pre-enrollment achievement measures, but they lack interpretability. We demonstrate how the predictions can be explained both globally and locally using IML methods including permutation importance (PI), partial dependence plot (PDP), LIME, and SHAP values.
Using global interpretations, we have found that the factor that has the greatest impact on academic performance is the high school grade point average, which measures general knowledge by taking into account grades in history, mathematics, Hungarian language and literature, a foreign language and a science subject. However, we also found that both mathematics and the subject of choice are among the most important variables, which suggests that program-specific knowledge is not negligible and complements general knowledge. We discovered that students are more likely to drop out if they do not start their university studies immediately after leaving secondary school. Using a partial dependence plot, we showed that humanities also have incremental predictive power, despite the fact that this analysis is based on data from a technical university. Finally, we also discuss the potential practical applications of our work, such as how the explanation of individual predictions allows for personalized interventions, for example by offering appropriate remedial courses and tutoring sessions. Our approach is unique in that we not only estimate the probability of dropping out, but also interpret the model and provide explanations for each prediction. As a result, this framework can be used in several fields. By predicting which majors they could be most successful in based on high school performance indicators, it might, for instance, assist high school students in selecting the appropriate programs at universities and hence this way it could be used for career assistance. Through the explanations of local predictions, the framework provided can also assist students in identifying the skills they need to develop to succeed in their university studies.
A tanulmány bemutatja a „Pannónia” dunántúli serdülőpszichiátriai multicentrikus, keresztmetszeti felmérés célkitűzéseit és eredményeit. A tervezett hét megyéből ötben sikerült a dunántúli régióban klinikai vizsgálatot végezni, s így felmérni minden új, egy év alatt a gondozóban jelentkező serdülő pszichiátriai beteget. A szerzők ismertetik a beteganyag diagnosztikai megoszlását, az elutasítási és lemorzsolódási arányt, a pszichiátriai betegségek kumulatív és egyes incidenciáit, továbbá közölnek néhány kisebbségre vonatkozó és egyéb demográfiai adatot is.
The present article drafts the changes that have taken place in German labour-force structure and labour market in the recent decades. Notwithstanding former trends, the number of university graduates started to decrease in the last five years. As reasons for this the author marks three main factors: demographic trends, decreasing interest in university carriers and the growing ratio of drop-outs. Considering vocational groups, he points out that indirect services and manufacturing cum maintenance services are on the rise, while regarding qualification groups he puts emphasis on the spreading of dual vocational education. In connection with this, the concept of “high-quality well-educated intellectuals” is revised, broadening the category to include also higher educational forms else than university and college education. The article also includes a comparison with an earlier prediction, concluding that automation had greater effects on the structure of labour than formerly expected.
Abstract
The problem of not having a language exam by the end of the university years affects thousands of students in Hungary. The literature reveals that this area is less researched, but there are a number of factors that I found important to examine. I did my research in the East Hungarian region. The reason for this is that many studies in this area have a higher rate of unsuccessful language learners than the rest of the country. I used online survey method in the form of a questionnaire, which consisted mostly of closed questions (alternative, selective and scale). My questions were focused on topics such as socioeconomic status, school life, language biography, cultural capital, language-specific social capital, language-learning type, affective characteristics, language pedagogy, drop-out and language learning attitudes. In this present study I highlight the effect of social and cultural effect on the success of language learning. During the query I used snowball method and address list query. As finding the target people proved to be very difficult, the number of elements is not significant (N = 202).
Tanulási utak a közoktatásban és a felsőoktatásban
Learning Paths in Public Education and Higher Education in Hungary
Absztrakt:
A tanulmány nemzetközi összefüggésben bemutatja azokat a továbbhaladással összefüggő trendeket és megközelítéseket, amelyek a kétezres évek eleje óta jelen vannak a magyar oktatásban. Kiemelten foglalkozik a lemorzsolódás, korai iskolaelhagyás jelenségével, azok oktatáspolitikai vetületével, valamint a tanulók, szülők továbbtanulási preferenciáival. Emellett az írás kitér a felsőoktatási trendekre, változásokra, hogyan alakult a felsőoktatáshoz való hozzáférés az ezredforduló óta, illetve milyen tipikus mintázatai vannak a felsőfokú továbbtanulásnak, a képzésben való továbbhaladásnak. A tanulmány foglalkozik a felsőfokú tanulmányok melletti kitartás és a lemorzsolódás jelenségének vizsgálati lehetőségeivel is.
appearance of the new student community and the importance of the integrated student groups. The third research was conducted by Gabriella Pusztai, Hajnalka Fenyes, Fruzsina Szigeti, and Katalin Pallay, mainly focusing on student who dropped out and also the
