d2klab / twitpersonality

TwitPersonality: Computing Personality Traits from Tweets using Word Embeddings and Supervised Learning

twitpersonality

twitpersonality implements 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.

How to Use

twitpersonality needs to learn from examples, first thing is to read training.

Once the models are created, then you can do some tests, please refer to test

How to Cite

Carducci G., Rizzo G., Monti D., Palumbo E., Morisio M. (2018) TwitPersonality: Computing Personality Traits from Tweets Using Word Embeddings and Supervised Learning. In Information volume 9 (5), 127

Licence

Apache License, Version 2.0. More details see LICENSE

twitpersonality's Issues

questionnaires.csv file

what is in this file questionnaires.csv and from where i can get this???

Advancement in Personality Patterns: Retweet/Reply and Follow Networks

1. When a Retweet/Reply network can be formed, it can be used used to correlate between personality, community affiliation, and role similarity https://arxiv.org/abs/1508.03165
2. When Tweets can be gathered, a Multiplex network can be formed based on topics and thus can be used to infer topical attitudes and sentiment/behavior contexts /https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7931960

scripts flow procedure

Can you tell me the scripts flow procedure for training dataset. and what is this fasttext dataset refers to???

Accuracy on tweets is much lower than reported in paper

HWhen reproducing the experiments using this code when trained on the ~10000 row dataset and testing against a users tweets, each user I test always get the ENFJ personality with all scores +/- 0.15 from:
Score for O is: 4.3
Score for C is: 3.4
Score for E is: 3.4
Score for A is: 3.6
Score for N is: 2.6
Jungian type is ENFJ

Do you have any idea why this may be?

I am using a mypersonality dataset with 9918 rows (excluding header) compared to your dataset with 9913 rows, however I think we may be using the same dataset and you removed a few rows?

Documentation: Feature Comparison between repos

There are other reports that includes tweet based classification features like Emotion and Sentiment https://github.com/monicamanda/twitter-personality-classification

Also just to note that there are other repos with similar features

• https://github.com/priyansh19/Classification-of-Personality-based-on-Users-Twitter-Data
• https://github.com/vishalbhalla/Twitter-User-Personality-Prediction
• https://github.com/rohilshah95/Twitter-Personalities
• https://github.com/sv6375261073/personality_detection