SENTIPEDE: A Smart System for Sentiment-based Personality Detection from Short Texts (original) (raw)
Related papers
A Hybrid Deep Learning Technique for Personality Trait Classification From Text
IEEE Access, 2021
Recently, Cognitive-based Sentiment Analysis with emphasis on automatic detection of user behaviour, such as personality traits, based on online social media text has gained a lot of attention. However, most of the existing works are based on conventional techniques, which are not sufficient to get promising results. In this research work, we propose a hybrid Deep Learning-based model, namely Convolutional Neural Network concatenated with Long Short-Term Memory, to show the effectiveness of the proposed model for 8 important personality traits (Introversion-Extroversion, Intuition-Sensing, Thinking-Feeling, Judging-Perceiving). We implemented our experimental evaluations on the benchmark dataset to accomplish the personality trait classification task. Evaluations of the datasets have shown better results, which demonstrates that the proposed model can effectively classify the user's personality traits as compared to the state-of-the-art techniques. Finally, we evaluate the effectiveness of our approach through statistical analysis. With the knowledge obtained from this research, organizations are capable of making their decisions regarding the recruitment of personals in an efficient way. Moreover, they can implement the information obtained from this research as best practices for the selection, management, and optimization of their policies, services, and products.
A Recurrent and Compositional Model for Personality Trait Recognition from Short Texts
2016
Many methods have been used to recognise author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e.g. linear regression or Support Vector Machines. This work uses deep-learning-based models and atomic features of text, the characters, to build hierarchical, vectorial word and sentence representations for trait inference. This method, applied to a corpus of tweets, shows state-of-the-art performance across five traits compared with prior work. The results, supported by preliminary visualisation work, are encouraging for the ability to detect complex human traits.
Personality Classification of text through Machine learning and Deep learning: A Review (2023)
Personality classification from text is a very popular domain of research among the domain of natural language processing. Personality of an individual has been found to be a very important characteristic when analyzing an individual for a particular purpose. Especially in fields such as e-recruitment, personality is a determining factor of if an individual has a placement at a particular workplace. The author aims to explore various personality classifications such as ‘The Big Five’ and the “Myer Briggs Type Indicator’ and various approaches in which text classification when it comes to detecting personality. Both machine learning and deep learning approaches are examined and their inner workings, benefits and limitations are detailed as well. We expect that this article will provide a thorough insight to personality classification of text by a numerous number of approaches.
International Journal of Engineering Research and Technology (IJERT), 2021
https://www.ijert.org/comparative-study-of-personality-prediction-from-social-media-by-using-machine-learning-and-deep-learning-method https://www.ijert.org/research/comparative-study-of-personality-prediction-from-social-media-by-using-machine-learning-and-deep-learning-method-IJERTCONV9IS07024.pdf The social media networks are an online forum that is used to improve social relationships with others by allowing people to share their thoughts, emotions, and experiences, among other things. The use of social media networks has skyrocketed in recent years. Predicting personality traits from social media networks has become a difficult challenge. This proposed approach uses social media networks to predict a person's personality. The big-fivefactor model (OCEAN) for defining personality is used in this project, which includes openness to experience (O), conscientiousness (C), extraversion (E), agreeableness (A), and neuroticism (N). The classification is done using machine learning and deep learning neural networks as classifiers. Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Decision Tree (DT) are machine learning classifiers and LSTM is deep learning classifier to predict a person's personality. We compare machine learning and deep learning personality prediction in this project. Finally, it was discovered that deep learning is more accurate than machine learning.
Personality Prediction from Social Media Posts using Text Embedding and Statistical Features
Computer Science and Information Systems (FedCSIS), 2019 Federated Conference on, 2022
Recent advances in deep learning based language models have boosted the performance in many downstream tasks such as sentiment analysis, text summarization, question answering, etc. Personality prediction from text is a relatively new task that has attracted researchers' attention due to the increased interest in personalized services as well as the availability of social media data. In this study, we propose a personality prediction system where text embeddings from large language models such as BERT are combined with multiple statistical features extracted from the input text. For the combination, we use the selfattention mechanism which is a popular choice when several information sources need to be merged together. Our experiments with the Kaggle dataset for MBTI clearly show that adding text statistical features improves the system performance relative to using only BERT embeddings. We also analyze the influence of the personality type words on the overall results.
Information
We are what we do, like, and say. Numerous research efforts have been pushed towards the automatic assessment of personality dimensions relying on a set of information gathered from social media platforms such as list of friends, interests of musics and movies, endorsements and likes an individual has ever performed. Turning this information into signals and giving them as inputs to supervised learning approaches has resulted in being particularly effective and accurate in computing personality traits and types. Despite the demonstrated accuracy of these approaches, the sheer amount of information needed to put in place such a methodology and access restrictions make them unfeasible to be used in a real usage scenario. In this paper, we propose a supervised learning approach to compute personality traits by only relying on what an individual tweets about publicly. The approach segments tweets in tokens, then it learns word vector representations as embeddings that are then used to feed a supervised learner classifier. We demonstrate the effectiveness of the approach by measuring the mean squared error of the learned model using an international benchmark of Facebook status updates. We also test the transfer learning predictive power of this model with an in-house built benchmark created by twenty four panelists who performed a state-of-the-art psychological survey and we observe a good conversion of the model while analyzing their Twitter posts towards the personality traits extracted from the survey.
Automated Personality Prediction of Social Media Users: A Decade Review
We live in a world where social media has taken over almost every possible field and has blended into our daily lives. People like to express their interests, thoughts, and views on these social networking sites. This information reveals many psychological aspects of their behaviour that can be used to predict their personality. Personality prediction is a very comprehensive and varied field of study. Over the years, there has been an ample amount of research done in this field. In this paper, we have tried to review the work carried out for personality prediction of social media users in the past decade using the information extracted from their digital footprints. Further, we have also discussed different machine and deep algorithms, datasets, personality measures, and applications of automatic personality detection. To understand the area better, we have done a case study where we used Convolutional Neural Networks model with word embeddings to predict the personality of 50 bloggers using the data accumulated from their blog posts around various topics such as beauty, fashion, travel, food, etc. We concluded that personality of Bloggers in the real world observed in their online columns, validating the hypothesis that the nature of online interactions does not greatly differ from that of real-world interactions.
International Journal of Recent Technology and Engineering (IJRTE), 2019
Persons express their sentiments as part of day-by-day communiqué. Personality traits reveals persons thoughts, about their feelings and persons behavior. Hence personality traits sets psychology how one person different from one another. Person thoughts expressed by what he/she write about any situation. Henceforth personality traits prediction is the vital research area. This research area belongs to NLP (Natural Language Processing), the most widely accepted of these traits are as: Openness (OPE), Conscientiousness (CON), Extraversion (EXT), Agreeableness (AGR), and Neuroticism (NEU). In this paper we have proposed to use time efficient sentence tokenization algorithm, efficient text preprocessing prominence on emoji’s followed by CNN deep learning classifier , proposed prediction model uses convolution filter for feature selection, further we have compared prediction model with machine learning based prediction model. We have also compared brute force tokenization method with pr...
The state-of-the-art in text-based automatic personality prediction
ArXiv, 2021
Personality detection is an old topic in psychology and Automatic Personality Prediction (or Perception) (APP) is the automated (computationally) forecasting of the personality on different types of human generated/exchanged contents (such as text, speech, image, video). The principal objective of this study is to offer a shallow (overall) review of natural language processing approaches on APP since 2010. With the advent of deep learning and following it transfer-learning and pre-trained model in NLP, APP research area has been a hot topic, so in this review, methods are categorized into three; pretrained independent, pre-trained model based, multimodal approaches. Also, to achieve a comprehensive comparison, reported results are informed by datasets.
Deep learning based personality recognition from Facebook status updates
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)
Many approaches have been proposed to automatically infer users personality from their social networks activities. However, the performance of these approaches depends heavily on the data representation. In this work, we apply deep learning methods to automatically learn suitable data representation for the personality recognition task. In our experiments, we used the Facebook status updates data. We investigated several neural network architectures such as fully-connected (FC) networks, convolutional networks (CNN) and recurrent networks (RNN) on the myPersonality shared task and compared them with some shallow learning algorithms. Our experiments showed that CNN with average pooling is better than both the RNN and FC. Convolutional architecturewith average pooling achieved the best results 60.0±6.5%.