دانلود مقاله یادگیری ماشینی در مطالعات هوش هیجانی
چکیده
مقدمه
پیش زمینه نظری
روش شناسی
نتایج
تحلیل و بحث
جهت گیری تحقیقات آینده
نتیجه گیری
منابع
Abstract
Introduction
Theoretical background
Methodology
Results
Analysis and discussion
Future research direction
Conclusion
References
چکیده
تحقیقات ثابت کرده است که داشتن سطح بالای هوش هیجانی (EI) می تواند احتمال ابتلا به بیماری روانی را کاهش دهد. EI و مؤلفه آن را می توان با آموزش بهبود بخشید، اما در حال حاضر این فرآیند انعطاف پذیری کمتری دارد و بسیار وقت گیر است. از سوی دیگر، یادگیری ماشینی (ML)، می‌تواند حجم عظیمی از داده‌ها را برای کشف روندها و الگوهای مفید در کوتاه‌ترین زمان ممکن تجزیه و تحلیل کند. با وجود مزایا، استفاده از ML در آموزش EI کمیاب است. در این مقاله، ما 92 مقاله مجلات را برای کشف روند استفاده از ML در مطالعه EI و اجزای آن مطالعه کردیم. این نظرسنجی با هدف هموار کردن راه برای مطالعات آینده است که می تواند منجر به پیاده سازی ML در آموزش EI شود، و به محققان در روانشناسی و علوم کامپیوتر کمک کند تا احتمالات داشتن یک الگوریتم ML عمومی برای هر مؤلفه EI را بیابند. یافته‌های ما روند رو به افزایشی را برای اعمال ML روی مؤلفه‌های EI نشان می‌دهد و ماشین بردار پشتیبان و شبکه عصبی دو الگوریتم ML محبوب‌ترین مورد استفاده در این تحقیقات هستند. ما همچنین دریافتیم که مهارت اجتماعی و همدلی کمترین مؤلفه های EI در معرض ML هستند. در نهایت، ما توصیه هایی برای جهت گیری تحقیقات آینده ML در حوزه EI و EI در ML ارائه می کنیم.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Research has proven that having high level of emotional intelligence (EI) can reduce the chance of getting mental illness. EI, and its component, can be improved with training, but currently the process is less flexible and very time-consuming. Machine learning (ML), on the other hand, can analyse huge amount of data to discover useful trends and patterns in shortest time possible. Despite the benefits, ML usage in EI training is scarce. In this paper, we studied 92 journal articles to discover the trend of the ML utilisation in the study of EI and its components. This survey aims to pave way for future studies that could lead to implementation of ML in EI training, and to rope in researchers in psychology and computer science to find possibilities of having a generic ML algorithm for every EI’s components. Our findings show an increasing trend to apply ML on EI components, and Support Vector Machine and Neural Network are the two most popular ML algorithms used in those researches. We also found that social skill and empathy are the least exposed EI components to ML. Finally, we provide recommendations for future research direction of ML in EI domain, and EI in ML.
Introduction
In 2001, WHO World Health reported that 450 million peoples are suffering from mental or behavioural disorder (WHO 2001). In their web article dated 22nd March 2018, they reported at least 300 million peoples are suffering from depression. Furthermore, they stated that every year, close to 800,000 peoples die from suicide, and this is the second highest death factor for 15–29- year-old. WHO estimated that in many countries, less than 10% of depressed individuals receive treatment (WHO 2018). Studies have shown that individuals with low emotional intelligence (EI) levels are more likely to feel depressed (Monteagudo et al. 2019), and depression leads to suicidal intention (Abdollahi et al. 2016). On the other hand, individuals with high EI are able to reduce problems related to depression (Marguerite et al. 2017). Additionally, quality life is often associated with high level of EI, and low level of EI is normally associated with undesirable behavioural outcome such as bullying, both in real life and online, substance abuse and suicidal intention (García-Sancho, Salguero, and Fernández-Berrocal 2015). These are among the reasons why research and development in EI should be given a serious consideration (García-Sancho, Salguero, and Fernández-Berrocal 2015).
Conclusion
Research efforts in applying and implementing ML in EI are still in their infancy. Nonetheless, it is extremely important to investigate how ML can be used to train someone’s EI due to the rising concern on mental health worldwide. Our survey aims to provide a clear understanding of the current state and trend in using ML in the EI studies. Our findings confirm that existing researches only addressed the application of ML on individual components of EI, and the trend of applying ML in those components is increasing over the years. This survey also found that the most preferred ML algorithms used in the current studies of EI’s components is Support Vector Machine (SVM) followed by Neural Network (NN) algorithms. The SVM algorithm has been applied in the studies of EI’ components except for social skills. On the other hand, random forest and k-means are the mostly preferred ML algorithms for social skill. Details on how SVM is implemented in each study need to be explored further to infer the possibility of its extension in order to serve as a generic algorithm for measuring EI. Another interesting finding is that among the six components of EI, social skill and empathy has limited exposure to ML, and more effort is needed to address this lacking. Finally, as there is an urgent need to use ML to train EI, and as EI comprises of the six components, it is crucial to develop the generic algorithm that can serve all the six components successfully. The availability of this algorithm would enable the development of an intelligent software agent to facilitate the EI training.