Personality Prediction of Social Network Users Using Ensemble and XGBoost

Abstract: Determining the image sentiment is a tedious task for classification algorithms, owing to complexities in the raw images as well as the intangible nature of human sentiments. Classifying image sentiments is an evergreen research area, especially in social data analytics. In current times, it is a common practice for majority people to precise their feelings on the web by substituting text with the upload of images via a multiplicity of social media sites like Facebook, Instagram, Twitter as well as any other platform. To identify the emotions from visual cues, some visual features as well as image processing techniques are used. Several existing systems have already introduced emotion detection using machine learning techniques, but the traditional feature extraction strategies do not achieve the required accuracy on random objects. In the entire process, normalization of image, feature extraction, and feature selection are important tasks in the train module. This work articulates the newest developments in the field of image sentiment employing deep learning techniques. Also, the use of conventional machine learning techniques is compared along with deep learning algorithms. It is indicative that a combination of fast recurrent neural networks and CNN may produce high accuracy with minimum time complexity. It is noted from the survey that existing researchers reflect CNN provides around 96.50% average accuracy for sentiment classification on the flicker image dataset.

Abstract: In general, humans are very complex organisms, and therefore, research into their various dimensions and aspects, including personality, has become an attractive subject of research. With the advent of technology, the emergence of a new kind of communication in the context of social networks has also given a new form of social communication to humans, and the recognition and categorization of people in this new space have become a hot topic of research that has been challenged by many researchers. In this paper, considering the Big Five personality characteristics of individuals, first, categorization of related work is proposed, and then a hybrid framework based on Fuzzy Neural Networks (FNN), along with, Deep Neural Networks (DNN) has been proposed that improves the accuracy of personality recognition by combining different FNN-classifiers with DNN-classifier in a proposed two-stage decision fusion scheme. Finally, a simulation of the proposed approach is carried out. The proposed approach is using the structural features of Social Networks Analysis (SNA), along with a linguistic analysis (LA) feature extracted from the description of the activities of individuals and comparison with the previous similar researches. The results, well-illustrated the performance improvement of the proposed framework up to 83.2 % of average accuracy on myPersonality dataset.

Abstract: Social network usage is growing exponentially every day. Different information are typically exchanged via social media platforms such as Facebook. User knowledge and what they have conveyed through changes in status are useful for learning about the behavior and human personality assessment. This work aims at setting up a framework that can predict the individual's personality based on Facebook user details. In order to analyze the individual's personality, big five model is used. The aim of this research is to predict the personality of user by using the status information present in their social media profile. Based on the analysis result, the user's personality is further classified into one of the categories present in the OCEAN model. The accuracy of personality prediction achieved by using Random Forest Classifier is 64.25%. The mean squared error is achieved using random forest regressor is 5.25.

Abstract: The content of social media (SM) is expanding quickly with individuals sharing their feelings in a variety of ways, all of which depict their personalities to varying degrees. This study endeavored to build a system that could predict an individual's personality through SM conversation. Four BIG5 personality items (i.e. Extraversion (EXT), Consciousness (CON), Agreeable (AGR) and Openness to Experiences (OPN) equivalent to the Myers–Briggs Type Indicator (MBTI)) were predicted using six supervised machine learning (SML) algorithms. In order to handle unstructured and unbalanced SM conversations, three feature extraction methods (i.e. term frequency and inverse document frequency (TF-IDF), the bag of words (BOW) and the global vector for word representation (GloVe)) were used. The TF-IDF method of feature extraction produces 2–9% higher accuracy than word2vec representation. GloVe is advocated as a better feature extractor because it maintains the spatial information of words.

Abstract: The growing use of social media among Internet users produces a vast and new source of user generated ecological data, such as textual posts and images, which can be collected for research purposes. The increasing convergence between social and computer sciences has led researchers to develop automated methods to extract and analyze these digital footprints to predict personality traits. These social media-based predictions can then be used for a variety of purposes, including tailoring online services to improve user experience, enhance recommender systems, and as a possible screening and implementation tool for public health. In this paper, we conduct a series of meta-analyses to determine the predictive power of digital footprints collected from social media over Big 5 personality traits. Further, we investigate the impact of different types of digital footprints on prediction accuracy. Results of analyses show that the predictive power of digital footprints over personality traits is in line with the standard “correlational upper-limit” for behavior to predict personality, with correlations ranging from 0.29 (Agreeableness) to 0.40 (Extraversion). Overall, our findings indicate that accuracy of predictions is consistent across Big 5 traits, and that accuracy improves when analyses include demographics and multiple types of digital footprints.

Abstract: A variety of approaches have been recently proposed to automatically infer users' personality from their user generated content in social media. Approaches differ in terms of the machine learning algorithms and the feature sets used, type of utilized footprint, and the social media environment used to collect the data. In this paper, we perform a comparative analysis of state-of-the-art computational personality recognition methods on a varied set of social media ground truth data from Facebook, Twitter and YouTube. We answer three questions: (1) Should personality prediction be treated as a multi-label prediction task (i.e., all personality traits of a given user are predicted at once), or should each trait be identified separately? (2) Which predictive features work well across different on-line environments? and (3) What is the decay in accuracy when porting models trained in one social media environment to another?

Abstract: User profiling in social media has gained a lot of attention due to its varied set of applications in advertising, marketing, recruiting, and law enforcement. Among the various techniques for user modeling, there is fairly limited work on how to merge multiple sources or modalities of user data - such as text, images, and relations - to arrive at more accurate user profiles. In this paper, we propose a deep learning approach that extracts and fuses information across different modalities. Our hybrid user profiling framework utilizes a shared representation between modalities to integrate three sources of data at the feature level, and combines the decision of separate networks that operate on each combination of data sources at the decision level. Our experimental results on more than 5K Facebook users demonstrate that our approach outperforms competing approaches for inferring age, gender and personality traits of social media users. We get highly accurate results with AUC values of more than 0.9 for the task of age prediction and 0.95 for the task of gender prediction.

Abstract: Suicidal ideation detection in online social networks is an emerging research area with major challenges. Recent research has shown that the publicly available information, spread across social media platforms, holds valuable indicators for effectively detecting individuals with suicidal intentions. The key challenge of suicide prevention is understanding and detecting the complex risk factors and warning signs that may precipitate the event. In this paper, we present a new approach that uses the social media platform Twitter to quantify suicide warning signs for individuals and to detect posts containing suicide-related content. The main originality of this approach is the automatic identification of sudden changes in a user's online behavior. To detect such changes, we combine natural language processing techniques to aggregate behavioral and textual features and pass these features through a martingale framework, which is widely used for change detection in data streams. Experiments show that our text-scoring approach effectively captures warning signs in text compared to traditional machine learning classifiers. Additionally, the application of the martingale framework highlights changes in online behavior and shows promise for detecting behavioral changes in at-risk individuals.

Abstract: The use of social networks is increasing rapidly. Various informations are shared widely through social media, i.e. Facebook. Information about users and what they expressed through status updates are such important assets for research in the field of behavioral learning and human personality. Similar researches have been conducted in this field and it grows continually till now. This study attempts to build a system that can predict a person’s personality based on Facebook user information. Personality model used in this research is Big Five Model Personality. While other previous researches used older machine learning algorithm in building their models, this research tries to implement some deep learning architectures to see the comparison by doing comprehensive analysis method through the accuracy result. The results succeeded to outperform the accuracy of previous similar research with the average accuracy of 74.17%.