Deep Learning-Based Document Modeling for Personality Detection from Text

  title={Deep Learning-Based Document Modeling for Personality Detection from Text},
  author={Navonil Majumder and Soujanya Poria and Alexander Gelbukh and E. Cambria},
  journal={IEEE Intelligent Systems},
This article presents a deep learning based method for determining the author's personality type from text: given a text, the presence or absence of the Big Five traits is detected in the author's psychological profile. [] Key Method Namely, the classifier is implemented as a specially designed deep convolutional neural network, with injection of the document-level Mairesse features, extracted directly from the text, into an inner layer.

Figures and Tables from this paper

A Hybrid Deep Learning Technique for Personality Trait Classification From Text

A hybrid Deep Learning-based model, namely Convolutional Neural Network concatenated with Long Short-Term Memory is proposed to show the effectiveness of the proposed model for 8 important personality traits, and Evaluations of the datasets have shown better results, which demonstrates that the model can effectively classify the user’s personality traits as compared to the state-of-the-art techniques.

Personality Detection from Text using Convolutional Neural Network

The overall performance showed by tanh is better than sigmoid and leaky ReLU for personality detection fromText based personality detection; however, tanh showed better result for others datasets.

Semantic-enhanced sequential modeling for personality trait recognition from texts

A novel semantic-enhanced personality recognition neural network (SEPRNN) model is proposed, which has a goal of avoiding dependence on feature engineering, allowing the same model to adapt to detecting five various personality traits with no modification to the model itself, and employing deep learning based methods and atomic features of texts to build vectorial word-level representation for personality trait recognition.

Encoding Text Information with Graph Convolutional Networks for Personality Recognition

The experimental results on two public and authoritative benchmark datasets show that the general personality GCN without any external word embeddings or knowledge is superior to the state-of-the-art methods for personality recognition.

Deep learning-based personality recognition from text posts of online social networks

Experimental results show that the deep semantic feature vectors learned from the proposed neural network are more effective than the other four kinds of non-trivial baseline features; the approach that utilizes the concatenation of the authors' deep semantic features and the statistical linguistic features as the input of the gradient boosting regression algorithm achieves the lowest average prediction error among all the approaches tested.

The state-of-the-art in text-based automatic personality prediction

This study offers a shallow (overall) review of natural language processing approaches on APP since 2010; pretrained independent, pre-trained model based, multimodal approaches.

Analysis of Personality Traits using Natural Language Processing and Deep Learning

This paper focuses on automating this task with the help of Neural Networks by using images instead of questions to accurately predict the personality type of users based on their responses on an interactive website in the form of a personality test.

Who Am I? Personality Detection Based on Deep Learning for Texts

This paper proposes a model named 2CLSTM, which is a bidirectional LSTMs (Long Short Term Memory networks) concatenated with CNN (Convolutional Neural Network), to detect user's personality using structures of texts to show that the structure of texts can be also an important feature in the study of personality detection from texts.

Automatic personality prediction: an enhanced method using ensemble modeling

Five new APP methods are suggested to enhance the accuracy of APP from the text through ensemble modeling (stacking) based on a hierarchical attention network (HAN) as the meta-model.

SENTIPEDE: A Smart System for Sentiment-based Personality Detection from Short Texts

The results support the prior findings of the tendency of persons with the same traits to express sentiments in similar ways, as well as gauging public perceptions underlying factors encompassing traits.



A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts

This work proposes to use deep-learning-based models with atomic features of text – the characters – to build hierarchical, vectorial word and sentence representations for the task of trait inference, and shows state-of-the-art performance on a corpus of tweets.

A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks

This work develops models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection and addresses the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.

Using Linguistic Cues for the Automatic Recognition of Personality in Conversation and Text

Experimental results for recognition of all Big Five personality traits, in both conversation and text, utilising both self and observer ratings of personality are reported, confirming previous findings linking language and personality, while revealing many new linguistic markers.

Affective Computing and Sentiment Analysis

  • E. Cambria
  • Computer Science
    IEEE Intelligent Systems
  • 2016
The emerging fields of affective computing and sentiment analysis, which leverage human-computer interaction, information retrieval, and multimodal signal processing for distilling people's sentiments from the ever-growing amount of online social data.

Using Hashtags to Capture Fine Emotion Categories from Tweets

It is shown that emotion‐word hashtags are good manual labels of emotions in tweets and a method to generate a large lexicon of word–emotion associations from this emotion‐labeled tweet corpus is proposed, which is the first lexicon with real‐valued word‐emotion association scores.

Multimodal Mood Classification Framework for Hindi Songs

A mood taxonomy is proposed and the framework for developing a multimodal dataset (audio and lyrics) for Hindi songs is described, which consists of three different systems based on the features of audio, lyrics and both.

Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon

This paper shows how to create a high-quality, moderate-sized emotion lexicon using Mechanical Turk, and identifies which emotions tend to be evoked simultaneously by the same term and shows that certain emotions indeed go hand in hand.


It is shown how the combined strength and wisdom of the crowds can be used to generate a large, high‐quality, word–emotion and word–polarity association lexicon quickly and inexpensively.

SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives

SenticNet 4 overcomes limitations by leveraging on conceptual primitives automatically generated by means of hierarchical clustering and dimensionality reduction.