Towards Understanding of User Perceptions for Smart Border Control Technologies using a Fine-Tuned Transformer Approach
Keywords:deep learning, machine learning, transformer models, transfer learning, NLP, border control technologies, sentiment analysis, user perceptions, BCPs
Smart Border Control (SBC) technologies became a hot topic in recent years when the European Union (EU) Commission announced the Smart Borders Package to improve the efficiency and security of the border crossing points (BCPs). Although, BCPs technologies have potential benefits in terms of enabling traveller' data processing, they still lead to acceptability and usability challenges when used by travelers. Success of technologies depends on user acceptance. Sentiment analysis is one of the primary techniques to measure user acceptance. Although, there exists variety of studies in literature where sentiment analysis has been used to understand user acceptance in different domains. To the best of our knowledge, there is no study where sentiment analysis has been used for measuring the user acceptance of SBC technologies. Thus, in this study, we propose a fine-tuned transformer model along with an automatic sentiment labels generation technique to perform sentiment analysis as a step towards getting insights into user acceptance of BCPs technologies. The results obtained in this study are promising; given the condition that there is no training data available from BCPs. The proposed approach was validated against IMDB reviews dataset and achieved weighted F1-score of 79% for sentiment analysis task.
M. Abomhara, S. Y. Yayilgan, A. H. Nymoen, M. Shalaginova, Z. Szekely, and O. Elezaj. Springer, 2019. doi: 10.1007/ 978-3-030-37545-4 7.
M. Abomhara, S. Y. Yayilgan, M. Shalaginova, and Z. Szekely. Border control and use of biometrics: reasons why the right to privacy can not be absolute. In IFIP International Summer School on Privacy and Identity Management, pages 259–271. Springer, Cham, 2019. doi: 10.1007/978-3-030-42504-3 17.
M. Abomhara, S. Y. Yayilgan, L. O. Nweke, and Z. Szekely. A comparison of primary stakeholders’ views on the deployment of biometric technologies in border management: Case study of smart mobility at the european land borders. Technology in Society, 64:101484, 2021. doi: 10.1016/j.techsoc.2020.101484.
A. Akbik, T. Bergmann, D. Blythe, K. Rasul, S. Schweter, and R. Vollgraf. Flair: An easy-to-use framework for state-of-the-art nlp. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 54–59, 2019. doi: 10.18653/ v1/N19-4010.
S. Alam and N. Yao. The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis. Computational and Mathematical Organization Theory, 25(3):319–335, 2019. doi: 10.1007/ s10588-018-9266-8.
S. Alshamrani, A. Abusnaina, M. Abuhamad, A. Lee, D. Nyang, and D. Mohaisen. An analysis of users engagement on twitter during the covid-19 pandemic: Topical trends and sentiments. In International Conference on Computational Data and Social Networks, pages 73–86. Springer, 2020. doi: 10.1007/ 978-3-030-66046-8 7.
M. M. Bradley and P. J. Lang. Affective norms for english words (anew): Instruction manual and affective ratings. Technical report, Technical report C-1, the center for research in psychophysiology..., 1999. Springer, 2013. doi: 10.1007/ 978-1-4471-5230-9.
E. Cho and J. Son. The effect of social connectedness on consumer adoption of social commerce in apparel shopping. Fashion and Textiles, 6(1):1–17, 2019. doi: 10.1186/ s40691-019-0171-7.
R. Cohen and D. Ruths. Classifying political orientation on twitter: It’s not easy! In Proceedings of the International AAAI Conference on Web and Social Media, volume 7, 2013.
Z. Dai, Z. Yang, Y. Yang, J. Carbonell, Q. V. Le, and R. Salakhutdinov. Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860, 2019. doi: 10.48550/arXiv.1901.02860.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. doi: 10.48550/arXiv.1810.04805.
X. T. Dinh and H. Van Pham. A proposal of deep learning model for classifying user interests on social networks. In Proceedings of the 4th International Conference on Machine Learning and Soft Computing, pages 10–14, 2020. doi: 10.1145/3380688.3380707.
V. Dutot, V. Bhatiasevi, and N. Bellallahom. Applying the technology acceptance model in a three-countries study of smartwatch adoption. The Journal of High Technology Management Research, 30(1):1–14, 2019. doi: 10. 1016/j.hitech.2019.02.001.
S. Feuerriegel and N. Proellochs. Sentimentanalysis vignette. Massachusetts Institute of Technology, 2019.
D. Folkinshteyn and M. Lennon. Braving bitcoin: A technology acceptance model (tam) analysis. Journal of Information Technology Case and Application Research, 18(4): 220–249, 2016. doi: 10.1080/15228053.2016. 1275242.
P. Budzianowski and I. Vulic. Hello, it’s gpt-2–how can i help you? towards the use of pretrained language models for taskoriented dialogue systems. arXiv preprint arXiv:1907.05774, 2019. doi: 10.48550/arXiv. 1907.05774.
R. Frontex. Best practice operational guidelines for automated border control (abc) systems. European Agency for the Management of Operational Cooperation, Research and Development Unit,. https://bit.ly/2KYBXhz Accessed, 9(05):2013, 2012.
P. Grover, A. K. Kar, M. Janssen, and P. V. Ilavarasan. Perceived usefulness, ease of use and user acceptance of blockchain technology for digital transactions–insights from usergenerated content on twitter. Enterprise Information Systems, 13(6):771–800, 2019. doi: 10.1080/17517575.2019.1599446.
M. Gupta, A. Bansal, B. Jain, J. Rochelle, A. Oak, and M. S. Jalali. Whether the weather will help us weather the covid-19 pandemic: Using machine learning to measure twitter users’ perceptions. International journal of medical informatics, 145:104340, 2021. doi: 10.1016/j.ijmedinf.2020.104340.
I. Guyon et al. A scaling law for the validationset training-set size ratio. AT&T Bell Laboratories, 1(11), 1997.
L. Hong and S. E. Page. Groups of diverse problem solvers can outperform groups of high-ability problem solvers. Proceedings of the National Academy of Sciences, 101 (46):16385–16389, 2004. doi: 10.1073/pnas. 0403723101.
C. Hutto and E. Gilbert. Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the International AAAI Conference on Web and Social Media, volume 8, 2014.
D. Jurgens, T. Finethy, J. McCorriston, Y. T. Xu, and D. Ruths. Geolocation prediction in twitter using social networks: A critical analysis and review of current practice. In Ninth international AAAI conference on web and social media, 2015.
S. Khan, K. Chopra, and P. Sharma. Brand review prediction using user sentiments: Machine learning algorithm. In 2nd International Conference on Data, Engineering and Applications (IDEA), pages 1–8. IEEE, 2020. doi: 10.1109/IDEA49133.2020.9170730. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142–150, Portland, Oregon, USA, June 2011. Association for Computational Linguistics. URL http://www.aclweb.org/anthology/P11-1015.
J. Maddock, K. Starbird, and R. M. Mason. Using historical twitter data for research: Ethical challenges of tweet deletions. In CSCW 2015 workshop on ethics for studying sociotechnical systems in a Big Data World. ACM, 2015.
L. Mathew and V. Bindu. Efficient classification techniques in sentiment analysis using transformers. In International Conference on Innovative Computing and Communications, pages 849–862. Springer, 2022. doi: 10.1007/978-981-16-2594-7 69.
Q. Mei, X. Shen, and C. Zhai. Automatic labeling of multinomial topic models. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 490–499, 2007. doi: 10.1145/1281192.1281246.
N. Memon. How biometric authentication poses new challenges to our security and privacy [in the spotlight]. IEEE Signal Processing Magazine, 34(4):196–194, 2017. doi: 10.1109/MSP.2017.2697179.
E. Mnif, K. Mouakhar, and A. Jarboui. Blockchain technology awareness on social media: Insights from twitter analytics. The Journal of High Technology Management Research, page 100416, 2021. doi: 10.1016/j.hitech.2021. 100416.
S. M. Mohammad and P. D. Turney. Crowdsourcing a word-emotion association lexicon. Computational Intelligence, 29(3):436– 465, 2013. doi: 10.1111/j.1467-8640.2012. 00460.x.
C. A. Lin and T. Kim. Predicting user response to sponsored advertising on social media via the technology acceptance model. Computers in Human Behavior, 64:710–718, 2016. doi: 10.1016/j.chb.2016.07.027.
S. Loria. textblob documentation. Release 0.15, 2:269, 2018.
A. L. Maas, R. E. Daly, P. T. Pham, D. Huang, A. Y. Ng, and C. Potts. Learning word vectors for sentiment analysis. In Proceedings
M. Molinari, D. Oxoli, C. Kilsedar, and M. Brovelli. User geolocated content analysis for urban studies: investigating mobility perception and hubs using twitter. In ISPRS Technical Commission IV Symposium 2018, volume 42, pages 439–442, 2018.
F. Morstatter, J. Pfeffer, H. Liu, and K. M. Carley. Is the sample good enough? comparing data from twitter’s streaming api with twitter’s firehose. In Seventh international AAAI conference on weblogs and social media, 2013.
A. Olteanu, C. Castillo, F. Diaz, and S. Vieweg. Crisislex: A lexicon for collecting and filtering microblogged communications in crises. In Eighth international AAAI conference on weblogs and social media, 2014.
A. Olteanu, A.-M. Kermarrec, and K. Aberer. Comparing the predictive capability of social and interest affinity for recommendations. In International Conference on Web Information Systems Engineering, pages 276–292. Springer, 2014. doi: 10.1007/978-3-319-11749-2 22.
K. Tomanek and U. Hahn. Semi-supervised active learning for sequence labeling. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 1039– 1047, 2009.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008, 2017.
A. Pandya, P. Kostakos, H. Mehmood, M. Cortes, E. Gilman, M. Oussalah, and S. Pirttikangas. Privacy preserving sentiment analysis on multiple edge data streams with apache nifi. In 2019 European Intelligence and Security Informatics Conference (EISIC), pages 130–133. IEEE, 2019. doi: 10.1109/ EISIC49498.2019.9108851.
V. Venkatesh, M. G. Morris, G. B. Davis, and F. D. Davis. User acceptance of information technology: Toward a unified view. MIS quarterly, pages 425–478, 2003. doi: 30036540.
D. M. Wegner. The illusion of conscious will. MIT press, 2017. doi: 10.1017/ S0140525X04000159.
W. Peng, S. Kanthawala, S. Yuan, and S. A. Hussain. A qualitative study of user perceptions of mobile health apps. BMC public health, 16(1):1–11, 2016. doi: 10.1186/ s12889-016-3808-0.
D. M. Powers. Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061, 2020. doi: 10.48550/arXiv. 2010.16061.
D. Rao, D. Yarowsky, A. Shreevats, and M. Gupta. Classifying latent user attributes in twitter. In Proceedings of the 2nd international workshop on Search and mining usergenerated contents, pages 37–44, 2010. doi: 10.1145/1871985.1871993.
R. Sanchis-Font, M. J. Castro-Bleda, J.-A. Gonzalez, F. Pla, and L.-F. Hurtado. Crossdomain polarity models to evaluate user experience in e-learning. Neural processing letters, pages 1–17, 2020. doi: 10.1007/ s11063-020-10260-5.
A. Willoughby. Biometric surveillance and the right to privacy [commentary]. IEEE Technology and Society Magazine, 36(3):41–45, 2017. doi: 10.1109/MTS.2017.2728736.
Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. R. Salakhutdinov, and Q. V. Le. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems, 32, 2019.
C. Ye and L. Zhao. Public perceptions of facebook’s libra digital currency initiative: Text mining on twitter. In Proceedings of the 54th Hawaii International Conference on System Sciences, page 5627, 2021. doi: 10.24251/ HICSS.2021.683.
S. Yoosuf and Y. Yang. Fine-grained propaganda detection with fine-tuned bert. In Proceedings of the second workshop on natural language processing for internet freedom: censorship, disinformation, and propaganda, pages 87–91, 2019. doi: 10.18653/v1/D19-5011.
A. P. Shiryaev, A. V. Dorofeev, A. R. Fedorov, L. G. Gagarina, and V. V. Zaycev. Lda models for finding trends in technical knowledge domain. In 2017 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), pages 551– 554. IEEE, 2017. doi: 10.1109/EIConRus. 2017.7910614.
Copyright (c) 2022 Sarang Shaikh, Sule Yildirim Yayilgan, Erjon Zoto, Mohamed Abomhara
This work is licensed under a Creative Commons Attribution 4.0 International License.