Fostering Cyber-Physical Social Systems through an Ontological Approach to Personality Classification Based on Social Media Posts

The exponential increase in social networks has led to emergent convergence of cyber-physical systems (CPS) and social computing, accelerating the creation of smart communities and smart organizations and enabling the concept of cyber-physical social systems. Social media platforms have made a significant contribution to what we call human behavior modeling. This paper presents a novel approach to developing a users’ segmentation tool for the Romanian language, based on the four DISC personality types, based on social media statement analysis. We propose and design the ontological modeling approach of the specific vocabulary for each personality and its mapping with text from posts on social networks. This research proposal adds significant value both in terms of scientific and technological contributions (by developing semantic technologies and tools), as well as in terms of business, social and economic impact (by supporting the investigation of smart communities in the context of cyber-physical social systems). For the validation of the model developed we used a dataset of almost 2000 posts retrieved from 10 social medial accounts (Facebook and Twitter) and we have obtained an accuracy of over 90% in identifying the personality profile of the users.

Supervised learning and resampling techniques on DISC personality classification using Twitter information in Bahasa Indonesia

PurposeGathering knowledge regarding personality traits has long been the interest of academics and researchers in the fields of psychology and in computer science. Analyzing profile data from personal social media accounts reduces data collection time, as this method does not require users to fill any questionnaires. A pure natural language processing (NLP) approach can give decent results, and its reliability can be improved by combining it with machine learning (as shown by previous studies).Design/methodology/approachIn this, cleaning the dataset and extracting relevant potential features “as assessed by psychological experts” are essential, as Indonesians tend to mix formal words, non-formal words, slang and abbreviations when writing social media posts. For this article, raw data were derived from a predefined dominance, influence, stability and conscientious (DISC) quiz website, returning 316,967 tweets from 1,244 Twitter accounts “filtered to include only personal and Indonesian-language accounts”. Using a combination of NLP techniques and machine learning, the authors aim to develop a better approach and more robust model, especially for the Indonesian language.FindingsThe authors find that employing a SMOTETomek re-sampling technique and hyperparameter tuning boosts the model’s performance on formalized datasets by 57% (as measured through the F1-score).Originality/valueThe process of cleaning dataset and extracting relevant potential features assessed by psychological experts from it are essential because Indonesian people tend to mix formal words, non-formal words, slang words and abbreviations when writing tweets. Organic data derived from a predefined DISC quiz website resulting 1244 records of Twitter accounts and 316.967 tweets.

XLNet-Caps: Personality Classification from Textual Posts

Personality characteristics represent the behavioral characteristics of a class of people. Social networking sites have a multitude of users, and the text messages generated by them convey a person’s feelings, thoughts, and emotions at a particular time. These social texts indeed record the long-term psychological activities of users, which can be used for research on personality recognition. However, most of the existing deep learning models for multi-label text classification consider long-distance semantics or sequential semantics, but problems such as non-continuous semantics are rarely studied. This paper proposed a deep learning framework that combined XLNet and the capsule network for personality classification (XLNet-Caps) from textual posts. Our personality classification was based on the Big Five personality theory and used the text information generated by the same user at different times. First, we used the XLNet model to extract the emotional features from the text information at each time point, and then, the extracted features were passed through the capsule network to extract the personality features further. Experimental results showed that our model can effectively classify personality and achieve the lowest average prediction error.

IDEAS OF HUMANIZATION OF PSYCHOLOGICAL RESEARCHES GIVEN IN THE WORK OF O.F. LAZURSKI «CLASSIFICATION OF PERSONALITIES» (TO THE CENTENARY OF THE FIRST EDITION)

This article’s aim is to attract the attention of specialists to the conceptual work of O.F. Lazurski “Classification of Personalities”, its first edition having been appeared posthumously in 1921. This edition being the continuation of the O.F.Lazurki’s book “Assay on the Science of Characters” was completed and prepared for publication by his pupils, M.Ya.Basov and V.M.Miasishchev; it disappeared at once from the book market due to the greatest public interest forcing the scientists to take care for two next editions in 1923 and 1925. Our article underlines the “Classification of Personalities” to be written in an epoch known by radical social consciousness transformation induced by dramatic and tragic events due to military and political factors of global scale having been acted in 1914-1918. The World War I, events of the first Russian revolution having begun earlier, in 1905, gave to the researcher, being these events direct witness and entity, unique materials for scientific analysis and generalization. In his directives concerning any event, the scientist realized the necessity of social life reformation. Such a thesis formulates his principal task and aim having been developed under the influence of serious trials, both physical and psychical, appeared to the society of that time. The article gives more precise and supplemented biographical data concerning the development of this scientist as a psychologist; it presents also a significantly widened list of O.F. Lazurski’s papers and their bibliographic descriptions. In such a way, we have obtained a possibility to find the sequence and systematization of his researches as well as his ideas evolution and his principal theoretical approaches having become basic for creating of his own theoretical notions. The authors have used the data taken from the scientist’s epistolary inheritance permitting the reconstruction of socio-cultural conditions during his work and the understanding of this work influence on the formation of O.F. Lazurkin’s own priority tasks during his work. We have discussed separately the principle of personality active adaptation to the environment being the basis of O.F. Lazurkin’s personality classification. Such an approach concerning the psychology of each human personality permits to understand the existence of two important subdivisions: there are three subdivisions on psychic (mental) level and a lot of them according to their different types and varieties according for each person mental contents. During the scientist’s text research, we have ascertained the central conception of the O.F. Lazurski’s “Classification of Personalities” to be a holistic personality description according to principles of systematization and scientific reliability. We note the author’s critical approach in understanding and generalization of personality classification having been existed in his epoch as well as theoretical backgrounds of sign classification describing each person’s various manifestations. We have especially emphasized the priority of ideas concerning personality research humanization in O.F. Lazurski works aiming to show each individual unique properties. The personality classification developed by O.F. Lazurski takes into consideration both psycho-physiological and socio-cultural components of each personality type due to understanding of each human personality as a whole organism, both physiological and social, including all its numerous interrelations and manifestations.