Supervised learning and resampling techniques on DISC personality classification using Twitter information in Bahasa Indonesia

Utami, Ema; Oyong, Irwan; Raharjo, Suwanto; Hartanto, Anggit Dwi; Adi, Sumarni

doi:10.1108/aci-03-2021-0054

Cited by 9 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It only resulted in an accuracy of 82.5%. Meanwhile, Utami et al [1] carried out a dataset balancing technique and used the SVC classification model. However, the accuracy tended to be low at 56%.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Data Mining Techniques in Handling Personality Analysis for Ideal Customers

Ramadhan¹,

Adiwijaya

2022

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

Background: Personality distinguishes individuals from one another, guides their actions and reactions, and dictates their preferences in many aspects of life, including shopping. Objective: This study determines the characteristics of an ideal customer based on individual personality. Methods: Data mining techniques used in this study are K-nearest neighbour (KNN), linear support vector machine (SVM), and random forest. This study also applies the synthetic minority oversampling technique (SMOTE) to overcome the imbalance in the amount of data. Results: This study shows that the application of the SMOTE and random forest models resulted in 88% accuracy, 79% precision, and 70% recall, which are the highest compared to other models. Conclusion: SMOTE in this research is unsuitable for use in the KNN and linear SVM classification models. Ensemble-based models such as random forest can produce high accuracy when SMOTE is applied for data pre-processing.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Personality is what distinguishes human beings from one another. It also guides actions, preferences, and behaviours [1] in many aspects of life, including shopping and consumption. Different consumers' behaviours are reflected in shopping lists from supermarkets, online shops, or souvenir outlets.…”

Section: Introductionmentioning

confidence: 99%

Data Mining Techniques in Handling Personality Analysis for Ideal Customers

Ramadhan¹,

Adiwijaya

2022

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

show abstract

“…The study offered a new sentiment analysis perspective but lacked a machine learning algorithm comparison [12]. Utami et al (2021) categorized DISC personality using Bahasa Indonesian Twitter data. Its single-language focus and limited dataset could restrict its broader applicability [13].…”

Section: Related Workmentioning

confidence: 99%

Customer Personality Analysis for Churn Prediction Using Hybrid Ensemble Models and Class Balancing Techniques

Ahmad,

Awan,

Nobanee

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Today's businesses rely heavily on focused marketing to improve their chances of growing and keeping their consumer base. Internet behemoths like Google and Facebook have expanded their business models around targeted advertisements that support business growth. Customer personality identification helps for churn prediction for companies. This problem arises in several companies where customer leaves companies for many reasons. This gap leads to conduct study for customer personality analysis. The collected dataset was highly imbalanced in nature. Two class balancing approaches CTGAN (Conditional tabular Generative adversarial networks) and SMOTE (Synthetic minority oversampling technique) has been utilized to equalize the both classes. There are three ensemble approaches such as bagging, boosting and stacking have been utilized for modeling purpose bagging approach uses Random Forest (RF) boosting utilizes XGBoost (XGB), Light Gradient Boosting Machine (LGBM) and ADA Boost (ADA B). The proposed Hybrid Model HSLR comprises of RF, XGB, ADA Boost, LGBM approaches as base classifiers and LR as a Meta classifier. Three testing independent set, k-fold with 5 and 10 folds have been utilized. To evaluate the performance of classifiers evaluation metrics such as Accuracy score, Precision, Recall, F1 score, MCC and ROC score have been utilized. The SMOTE generated data has shown results as compare with CTGAN generated data. The SMOTE approach has shown the highest results of 94.06, 94.23, 94.28, 94.05, 88.13 and 0.984 as accuracy score, Precision, recall, F1, MCC and Roc score respectively.

show abstract

“…The stemming technique used in this study was the stemming algorithm introduced by [19]. Some Twitter users in Indonesia use non-standard language (slang) in making tweets [20]. In this study, a slang word dictionary published by authors [21] was tested.…”

Section: Data Preprocessingmentioning

confidence: 99%

Sentiment Analysis and Topic Modelling of The COVID-19 Vaccine in Indonesia on Twitter Social Media Using Word Embedding

Agustiningsih

Utami²,

Alsyaibani³

2022

Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika

View full text Add to dashboard Cite

This study aims to analyze the sentiments of the Indonesian people towards the COVID-19 vaccine on Twitter. Data collection was carried out from September 2020 to June 2021 with the keyword "covid vaccine," which resulted in 262306 tweets. After filtering and cleaning, there are 83384 tweets left. The labeling process was done manually by an expert. The label composition in the data is 35209 tweets of positive sentiment, 41596 tweets of neutral sentiment, and 6579 tweets of negative sentiment. The remaining data is preprocessed using case folding, removing punctuation, stopword removal, stemming, and the application of slang words. The highest number of tweets appeared in January 2021, after Joko Widodo became the first person in Indonesia to receive a vaccine injection. The number of tweets reached 23492 tweets. At the topic modeling stage, measurements were conducted using the Coherence Score. The distribution of the optimal number of topics is 3 topics. The first topic, with a token percentage value of 51.8%, leads to positive sentiment, while the second and third topics, with token percentage values of 24.5% and 23.7%, lead to neutral sentiment. Bidirectional LSTM architecture was implemented to perform sentiment classification. Fasttext and GloVe word embedding was tested to vectorize tweet data. The test accuracy generated by Fasttext word embedding reached 75,7690%, while the test accuracy produced with GloVe word embedding reached 74.7017%. The usage of slang words could not increase the test accuracy in this study. The use of the Modelcheckpoint to monitor model performance during training could produce a model with a slightly higher test accuracy, about 1.07% (in scenario 1 and scenario 6), compared to a model whose performance was monitored using Early Stopping. In future research, it can be tried to apply a lower learning rate to produce better accuracy in a large number of epochs, or it could be by changing the dropout parameter.

show abstract

Supervised learning and resampling techniques on DISC personality classification using Twitter information in Bahasa Indonesia

Cited by 9 publications

References 23 publications

Data Mining Techniques in Handling Personality Analysis for Ideal Customers

Data Mining Techniques in Handling Personality Analysis for Ideal Customers

Customer Personality Analysis for Churn Prediction Using Hybrid Ensemble Models and Class Balancing Techniques

Sentiment Analysis and Topic Modelling of The COVID-19 Vaccine in Indonesia on Twitter Social Media Using Word Embedding

Contact Info

Product

Resources

About