Bottom-Up and Top-Down: Predicting Personality with Psycholinguistic and Language Model Features

Mehta, Yash; Fatehi, Samin; Kazameini, Amirmohammad; Stachl, Clemens; Wang, Zhaoxia; Eetemadi, Sauleh

doi:10.1109/icdm50108.2020.00146

Cited by 76 publications

(51 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset only contained two columns, one is the user MBTI type, and another is their respective posts on Personality Cafe forum. Five researches on the same dataset were identified, namely Cui & Qi (2017), Bharadwaj et al (2018), Li et al (2018), Mehta et al (2020) and Amirhosseini & Kazemian (2020). The justifications on the reasons of choosing this dataset are as follows:…”

Section: Datasetmentioning

confidence: 99%

“…However, that cannot be reproduced with Kaggle-Filtered dataset with MBTI keyword removed. Four researches, Cui & Qi (2017), Bharadwaj et al (2018), Li et al (2018) and Mehta et al (2020) did not mention explicitly about removal of MBTI keyword in their preprocessing step. Only Amirhosseini & Kazemian (2020) mentioned removal of MBTI keywords in their preprocessing steps.…”

Section: Benchmarking With Previous Researchesmentioning

confidence: 99%

“…Referring to Table 1 in the related works section, best performing algorithm from Cui & Qi (2017), Bharadwaj et al (2018), Li et al (2018), Mehta et al (2020) and Amirhosseini & Kazemian (2020) are long short-term memory (LSTM), support vector machine (SVM), k nearest neighbor (KNN), BERT + MLP and XGBoost. LightGBM used in this research achieved 81.68% accuracy with a standard deviation of 1.09%, and had outperformed the accuracy of all previous work on this dataset as indicated in Table 5.…”

Section: Benchmarking With Previous Researchesmentioning

confidence: 99%

See 2 more Smart Citations

Predicting judging-perceiving of Myers-Briggs Type Indicator (MBTI) in online social forum

Choong

Varathan

2021

PeerJ

View full text Add to dashboard Cite

The Myers-Briggs Type Indicator (MBTI) is a well-known personality test that assigns a personality type to a user by using four traits dichotomies. For many years, people have used MBTI as an instrument to develop self-awareness and to guide their personal decisions. Previous researches have good successes in predicting Extraversion-Introversion (E/I), Sensing-Intuition (S/N) and Thinking-Feeling (T/F) dichotomies from textual data but struggled to do so with Judging-Perceiving (J/P) dichotomy. J/P dichotomy in MBTI is a non-separable part of MBTI that have significant inference on human behavior, perception and decision towards their surroundings. It is an assessment on how someone interacts with the world when making decision. This research was set out to evaluate the performance of the individual features and classifiers for J/P dichotomy in personality computing. At the end, data leakage was found in dataset originating from the Personality Forum Café, which was used in recent researches. The results obtained from the previous research on this dataset were suggested to be overly optimistic. Using the same settings, this research managed to outperform previous researches. Five machine learning algorithms were compared, and LightGBM model was recommended for the task of predicting J/P dichotomy in MBTI personality computing.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Benchmarking With Previous Researchesmentioning

confidence: 99%

Section: Benchmarking With Previous Researchesmentioning

confidence: 99%

See 1 more Smart Citation

Predicting judging-perceiving of Myers-Briggs Type Indicator (MBTI) in online social forum

Choong

Varathan

2021

PeerJ

View full text Add to dashboard Cite

show abstract

“…In particular, this is justified by the fact that trendy modern pedagogical concepts such as 'self-directed', 'inquiry-based', and 'student agency' are all integrated within bottom-up education as an umbrella term. Mehta et al (2020) consider the bottom-up approach to be the basis of the strategy for personal development and a part of the deep learning process.…”

Section: General Insights Of the Problem Articulationmentioning

confidence: 99%

Implementation of the Social Component of Higher Education: Bottom-up Approach

Marushkevych

Zvarych

Lavrychenko

et al. 2021

IJLTER

View full text Add to dashboard Cite

Pedagogical strategies for the implementation of the social content of higher education should be exercised through the application of the bottom-up approach. The bottom-up approach is aimed at ensuring proper development of the student’s personality. This approach is based on the subject-specific (academic achievements) and generic (leadership, management skills and focus on personal and professional development) competencies. The purpose of this study was to investigate the range of tools as well as the effectiveness of the bottom-up approach to the implementation of the social component of higher education through perspective development and the emphasis on students’ leadership and management skills. The study is of an empirical nature and the research component is based on the formative experimental methodology. Fifteen students of the Faculty of Primary Education participated in the experimental part of the study. They were involved in the specific bottom-up approach to educational environment organization and were evaluated accordingly by a jury. The two-year implementation period of the bottom-up approach to the implementation of the social content of higher education took place through customized projects of personal and professional development. The average socialization readiness level within the group was 78.2 (out of 100 max.), with 13.3% of students showing an average socialization readiness level, and 86.7% of students achieving a good level. The results confirmed the effectiveness of the principal notions of the study. The task of adapting the content of higher education in order to achieve a positive momentum of students’ socialization readiness was successfully completed. The most promising approach for future research is finding out the advisability and effectiveness of expanding the range of participants of the projects of personal and professional self-development and leadership with the preservation of the essence and identified values of the bottom-up approach.

show abstract

“…Third, cloud computing is subject to a weak and still under-development regulation. Accordingly, privacy concerns arise especially when one recalls that emotion recognition and sentiment analysis allow for user profiling [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition on Edge Devices: Training and Deployment

Pandelea

Ragusa

Apicella

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.

show abstract

Bottom-Up and Top-Down: Predicting Personality with Psycholinguistic and Language Model Features

Cited by 76 publications

References 40 publications

Predicting judging-perceiving of Myers-Briggs Type Indicator (MBTI) in online social forum

Predicting judging-perceiving of Myers-Briggs Type Indicator (MBTI) in online social forum

Implementation of the Social Component of Higher Education: Bottom-up Approach

Emotion Recognition on Edge Devices: Training and Deployment

Contact Info

Product

Resources

About