(Department of Electrical Engineering and Informatics, Faculty of Engineering, Universitas Negeri Malang, Indonesia)(2) * Aji Prasetya Wibawa
(Department of Electrical Engineering and Informatics, Faculty of Engineering, Universitas Negeri Malang, Indonesia)(3) Suyono Suyono
(Department of Indonesian Literature, Faculty of Letters, Universitas Negeri Malang, Indonesia)(4) Fachrul Kurniawan
(Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Indonesia)(5) Roman Voliansky
(National Technical University of Ukraine, Igor Sikorsky Kyiv Polytechnic Institute, Ukraine)(6) Korhan Cengiz
(Associate Professor, Department of Electrical Engineering, Biruni University, Istanbul, Turkey)*corresponding author
AbstractIdentifying humor in stand-up comedy texts has distinct issues due to humor's subjective and context-dependent characteristics. This study introduces an innovative method for humor retention in stand-up comedy content by employing a pre-trained BERT model that has been fine-tuned for humor classification. The process commences with the collection and annotation of a varied assortment of stand-up comedy writings, categorized as hilarious or non-humorous, with essential comic elements like punchlines and setups highlighted to augment the model's comprehension of humor. The texts undergo preprocessing and tokenization to be ready for input into the BERT model. Upon refining the model using the annotated dataset, predictions regarding humor retention are generated for each text, yielding classifications and confidence scores that reflect the model's certainty in its predictions. The criterion for prediction confidence is set to categorize texts as "retaining humor." The results indicate that prediction confidence is a dependable metric for humor retention, with elevated confidence scores associated with enhanced accuracy in comedy classification. Nonetheless, the analysis reveals that text length does not affect the model's confidence much, contradicting the presumption that lengthier texts are more prone to comedy. The findings underscore the significance of environmental and linguistic elements in comedy detection, indicating opportunities for model enhancement. Future efforts will concentrate on augmenting the dataset to encompass a broader range of comic styles and integrating more contextual variables to improve prediction accuracy, especially in intricate or ambiguous comedic situations
KeywordsBERT Model Fine-Tuning; Humor Detection; Humor Retention Prediction; Stand-Up Comedy; Text Preprocessing
|
DOIhttps://doi.org/10.31763/sitech.v5i2.1812 |
Article metrics10.31763/sitech.v5i2.1812 Abstract views : 22 | PDF views : 13 |
Cite |
Full Text Download
|
References
[1] D. M. Beskow, S. Kumar, and K. M. Carley, “The evolution of political memes: Detecting and characterizing internet memes with multi-modal deep learning,” Inf. Process. Manag., vol. 57, no. 2, p. 102170, 2020, doi: 10.1016/j.ipm.2019.102170.
[2] K. Tomaž and W. Walanchalee, “One does not simply … project a destination image within a participatory culture,” J. Destin. Mark. Manag., vol. 18, p. 100494, 2020, doi: 10.1016/j.jdmm.2020.100494.
[3] Supriyono, A. P. Wibawa, Suyono, and F. Kurniawan, “Analyzing Audience Sentiments in Digital Comedy: A Study of YouTube Comments Using LSTM Models,” J. Appl. Data Sci., vol. 5, no. 4, pp. 1877–1889, 2024, doi: 10.47738/jads.v5i4.393.
[4] L. Kang, P. Riba, M. Rusiñol, A. Fornés, and M. Villegas, “Pay attention to what you read: Non-recurrent handwritten text-Line recognition,” Pattern Recognit., vol. 129, p. 108766, 2022, doi: 10.1016/j.patcog.2022.108766.
[5] S. Islam et al., “A comprehensive survey on applications of transformers for deep learning tasks,” Expert Syst. Appl., vol. 241, p. 122666, 2024, doi: 10.1016/j.eswa.2023.122666.
[6] A. P. Wibawa, H. K. Fithri, I. A. E. Zaeni, and A. Nafalski, “Generating Javanese Stopwords List using K-means Clustering Algorithm,” Knowl. Eng. Data Sci., vol. 3, no. 2, p. 106, Dec. 2020, doi: 10.17977/um018v3i22020p106-111.
[7] O. Vinzelberg, M. D. Jenkins, G. Morison, D. McMinn, and Z. Tieges, “Lay Text Summarisation Using Natural Language Processing: A Narrative Literature Review,” J. Japanese Soc. Clin. Cytol., vol. 43, no. 1, p. 202, 2023. [Online]. Available at: https://arxiv.org/abs/2303.14222.
[8] C. Bertram, Z. Weiss, L. Zachrich, and R. Ziai, “Artificial intelligence in history education. Linguistic content and complexity analyses of student writings in the CAHisT project (Computational assessment of historical thinking),” Comput. Educ. Artif. Intell., p. 100038, 2021, doi: 10.1016/j.caeai.2021.100038.
[9] M. Mulyadi, M. Yusuf, and R. K. Siregar, “Verbal humor in selected Indonesian stand up comedian’s discourse: Semantic analysis using GVTH,” Cogent Arts Humanit., vol. 8, no. 1, Jan. 2021, doi: 10.1080/23311983.2021.1943927.
[10] T. Widiyaningtyas, A. P. Wibawa, W. Caesarendra, and U. Pujianto, “MF-NCG: Recommendation Algorithm Using Matrix Factorization-based Normalized Cumulative Genre,” Int. J. Intell. Eng. Syst., vol. 17, no. 2, pp. 180–189, 2024, doi: 10.22266/ijies2024.0430.16.
[11] “Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions,” IEEE Access, vol. 10, pp. 86038–86056, 2022, doi: 10.1109/access.2022.3197769.
[12] L. Stankevičius and M. Lukoševičius, “Extracting Sentence Embeddings from Pretrained Transformer Models,” Appl. Sci., vol. 14, no. 19, p. 8887, Oct. 2024, doi: 10.3390/app14198887.
[13] A. A. Coolidge, C. Montagnolo, and S. Attardo, “Comedic convergence: Humor responses to verbal irony in text messages,” Lang. Sci., vol. 99, p. 101566, 2023, doi: 10.1016/j.langsci.2023.101566.
[14] S. Ben Slama and M. Mahmoud, “A deep learning model for intelligent home energy management system using renewable energy,” Eng. Appl. Artif. Intell., vol. 123, p. 106388, 2023, doi: 10.1016/j.engappai.2023.106388.
[15] L. Sadozai, S. Prot-Labarthe, O. Bourdon, S. Dauger, and A. Deho, “Use of continuous infusion of clonidine for sedation in critically ill infants and children,” Arch. Pédiatrie, vol. 29, no. 2, pp. 116–120, 2022, doi: 10.1016/j.arcped.2021.11.015.
[16] Y. Chen and S. Eger, “Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End,” no. v, pp. 62–84, 2024, doi: 10.18653/v1/2023.eval4nlp-1.6.
[17] L. Xiao, H. He, and Y. Jin, “FusionSum: Abstractive summarization with sentence fusion and cooperative reinforcement learning,” Knowledge-Based Syst., vol. 243, p. 108483, 2022, doi: 10.1016/j.knosys.2022.108483.
[18] A. B. Alawi and F. Bozkurt, “A hybrid machine learning model for sentiment analysis and satisfaction assessment with Turkish universities using Twitter data,” Decis. Anal. J., vol. 11, p. 100473, 2024, doi: 10.1016/j.dajour.2024.100473.
[19] M. Davis et al., “OGITO, an Open Geospatial Interactive Tool to support collaborative spatial planning with a maptable,” Procedia Comput. Sci., vol. 227, no. 1, pp. 591–598, 2023, doi: 10.1016/j.geoforum.2023.103848.
[20] J. Younes et al., “Efficient CRNN: Towards end-to-end low resource Urdu text recognition using depthwise separable convolutions and gated recurrent units,” Speech Commun., vol. 136, no. 3, pp. 764–788, 2024, doi: 10.1016/j.jbi.2022.103998.
[21] A. P. Wibawa, A. B. P. Utama, H. Elmunsyah, U. Pujianto, F. A. Dwiyanto, and L. Hernandez, “Time-series analysis with smoothed Convolutional Neural Network,” J. Big Data, vol. 9, no. 1, p. 44, Dec. 2022, doi: 10.1186/s40537-022-00599-y.
[22] Q. Hu, Y. Zhang, X. Zhang, Z. Han, and X. Liang, “Language fusion via adapters for low-resource speech recognition,” Speech Commun., vol. 158, p. 103037, 2024, doi: 10.1016/j.specom.2024.103037.
[23] A. Hussain, S. U. Khan, I. Rida, N. Khan, and S. W. Baik, “Human centric attention with deep multiscale feature fusion framework for activity recognition in Internet of Medical Things,” Inf. Fusion, vol. 106, p. 102211, 2024, doi: 10.1016/j.inffus.2023.102211.
[24] S. Shi, K. Hu, J. Xie, Y. Guo, and H. Wu, “Robust scientific text classification using prompt tuning based on data augmentation with L2 regularization,” Inf. Process. Manag., vol. 61, no. 1, p. 103531, 2024, doi: 10.1016/j.ipm.2023.103531.
[25] S. Heo and J. Park, “Are you satisfied or satiated by the games you play? An empirical study about game play and purchase patterns by genres,” Telemat. Informatics, vol. 59, p. 101550, 2021, doi: 10.1016/j.tele.2020.101550.
[26] G. G. Al-Khateeb, A. Alnaqbi, and W. Zeiada, “Statistical and machine learning models for predicting spalling in CRCP,” Sci. Rep., vol. 14, no. 1, p. 21301, Sep. 2024, doi: 10.1038/s41598-024-69999-9.
[27] P. Sikström, C. Valentini, A. Sivunen, and T. Kärkkäinen, “How pedagogical agents communicate with students: A two-phase systematic review,” Comput. Educ., vol. 188, p. 104564, 2022, doi: 10.1016/j.compedu.2022.104564.
[28] M. Mir and P. Laskurain-Ibarluzea, “Spanish and English Verbal Humour: A Comparative Study of Late-night Talk Show Monologues,” Contrastive Pragmat., vol. 3, no. 2022, pp. 278–312, 2022, doi: 10.1163/26660393-bja10035.
[29] D. A. Sulistyo, “LSTM-Based Machine Translation for Madurese-Indonesian,” J. Appl. Data Sci., vol. 4, no. 3, pp. 189–199, Sep. 2023, doi: 10.47738/jads.v4i3.113.
[30] E. M. Saoudi, J. Jaafari, and S. J. Andaloussi, “Advancing human action recognition: A hybrid approach using attention-based LSTM and 3D CNN,” Sci. African, vol. 21, p. e01796, 2023, doi: 10.1016/j.sciaf.2023.e01796.Refbacks
- There are currently no refbacks.
Copyright (c) 2025 Supriyono Supriyono, Aji Prasetya Wibawa, Suyono Suyono, Fachrul Kurniawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
Science in Information Technology Letters
ISSN 2722-4139
Published by Association for Scientific Computing Electrical and Engineering (ASCEE)
W : http://pubs2.ascee.org/index.php/sitech
E : sitech@ascee.org, andri@ascee.org, andri.pranolo.id@ieee.org
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0