پيش بيني كننده درجه(ميزان) شادكامي با استفاده از ساختار داده مفهومي براي معماري هاي يادگيري عميق

A happiness degree predictor using the conceptual data structure for deep learning architectures

پيشينه و هدف شادكامي يك هدف انساني اساسي جهاني است از زمان ظهور روانشناسي مثبت تمركز اصلي در تحقيقات روان شناختي بررسي نقش عوامل تعيين كننده در پيش بيني شادكامي بوده است روش‌هاي متداول مبتني بر روابط خطي هستند مانند رگرسيون خطي چند نتغييره متداول كخ ممكن است از عدم توانايي بازنمود ويژگي هاي روانشناختي متنوع رنج ببرند.با استفاده از شبكه هاي عصبي عميق ما يو پيش بيني كننده درجه شادكامي را بر اساس پاسخ به پنج پرسشنامه استاندارد درون سنجي تعريف مي كنيم. روش ها:سي معماري ساختار داده محور براي به منظور تعريف يك HDP پيشنهاد شده است كه در آن معماري شبكه امكان تفسير مفهومي از عوامل روانشناختي مرتبط با شادكامي را فراهم مي‌كند.چهار پيكربندي شبكه عصبي مختلف با تغيير دادن تعداد نرون ها و وجود يا عدم وجود باياس در لايه هاي پنهان آزمايش شده است دو معيار براي ارزيابي تاثير ابعاد مفهومي تعريف و محاسبه شده است يكي وزن موثر بعد مفهومي را به صورت عبارت مطلق معين ني كند و ديگري به جهت مثبت يا منفي اثر اشاره مي كند.

Background and Objective: Happiness is a universal fundamental human goal. Since the emergence of Positive Psychology, a major focus in psychological research has been to study the role of certain factors in the prediction of happiness. The conventional methodologies are based on linear relationships, such as the commonly used Multivariate Linear Regression (MLR), which may suffer from the lack of representative capacity to the varied psychological features. Using Deep Neural Networks (DNN), we define a Happiness Degree Predictor (H-DP) based on the answers to five psychometric standardized questionnaires. Methods: A Data-Structure driven architecture for DNNs (D-SDNN) is proposed for defining a HDP in which the network architecture enables the conceptual interpretation of psychological factors associated to happiness. Four different neural network configurations have been tested, varying the number of neurons and the presence or absence of bias in the hidden layers. Two metrics for evaluating the influence of conceptual dimensions have been defined and computed: one quantifies the influence weight of the conceptual dimension in absolute terms and the other one pinpoints the direction (positive or negative) of the influence. Materials: A cross-sectional survey targeting non-institutionalized adult population residing in Spain was completed by 823 cases. The total of 111 elements of the survey are grouped by socio-demographic data and by five psychometric scales (Brief COPE Inventory, EPQR-A, GHQ-28, MOS-SSS and SDHS) measuring several psychological factors acting one as the outcome (SDHS) and the four others as predictors. Results: Our D-SDNN approach provided a better outcome (MSE: 1.46 · 10?2) than MLR (MSE: 2.30 · 10?2), hence improving by 37% the predictive accuracy, and allowing to simulate the conceptual structure. Conclusions: We observe a better performance of Deep Neural Networks (DNN) with respect to traditional methodologies. This demonstrates its capability to capture the conceptual structure for predicting happiness degree through psychological variables assessed by standardized questionnaires. It also permits to estimate the influence of each factor on the outcome without assuming a linear relationship.