Abstract
The semantic analysis is an important tool for processing people’s opinions, but processing data from social networking sites like Twitter is still challenging. Transit related tweets in London and Prague collected during the COVID-19 pandemic were analyzed using two corpus-based approaches – Bag-of-Words and Latent Dirichlet Allocation. Punctuality was the most frequent issue in both cities, followed by COVID-19 in London and Comfort in Prague. Analysis for the busiest London station enhanced the importance of the Breakdowns topic. Specific issues were found for some stations such as Victoria Station in London. The BoW method in our cases provides more robust results, namely for large heterogeneous samples, while LDA is well-suited for topic extraction using narrow well-specified samples focused on the explored theme.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Almohammad, A., Georgakis, P.: Public twitter data and transport network status. In: 2020 10th International Conference on Information Science and Technology (ICIST). IEEE, Bath, London, and Plymouth, United Kingdom, pp. 169–174 (2020)
Alshehri, A., O’Keefe, R.: Analyzing social media to assess user satisfaction with transport for London’s oyster. Int. J. Hum.-Comput. Interact. 35, 1378–1387 (2019). https://doi.org/10.1080/10447318.2018.1526442
Anthony, A.: To mask or not to mask? Opinion split on London underground. The Observer (2021)
Azizi, F., Hajiabadi, H., Vahdat-Nejad, H., Khosravi, M.H.: Detecting and analyzing topics of massive COVID-19 related tweets for various countries. Comput. Electr. Eng. 106, 108561 (2023). https://doi.org/10.1016/j.compeleceng.2022.108561
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003). Submitted 2/02; Published 1/03
Brzustewicz, P., Singh, A.: Sustainable consumption in consumer behavior in the time of COVID-19: topic modeling on twitter data using LDA. Energies 14, 5787 (2021). https://doi.org/10.3390/en14185787
Dahal, B., Kumar, S.A.P., Li, Z.: Topic modeling and sentiment analysis of global climate change tweets. Soc. Netw. Anal. Min. 9, 24 (2019). https://doi.org/10.1007/s13278-019-0568-8
Davis, C.A., Fonseca, F.T.: Assessing the certainty of locations produced by an address geocoding system. GeoInformatica 11, 103–129 (2007). https://doi.org/10.1007/s10707-006-0015-7
Garcia-Martinez, A., Cascajo, R., Jara-Diaz, S.R., Chowdhury, S., Monzon, A.: Transfer penalties in multimodal public transport networks. Transp. Res. Part Policy Pract. 114, 52–66 (2018). https://doi.org/10.1016/j.tra.2018.01.016
Georgiadis, G., Nikolaidou, A., Politis, I., Papaioannou, P.: How public transport could benefit from social media? evidence from european agencies. In: Nathanail, E.G., Adamos, G., Karakikes, I. (eds.) Advances in Mobility-as-a-Service Systems, pp. 645–653. Springer International Publishing, Cham (2021)
Howard, J.M.: Trains, Twitter and the social licence to operate: an analysis of Twitter use by train operating companies in the United Kingdom. Case Stud. Transp. Policy 8, 812–821 (2020). https://doi.org/10.1016/j.cstp.2020.06.002
Huang, J.-W., Ma, H.-S., Chung, C.-C., Jian, Z.-J.: Unknown but interesting recommendation using social penetration. Soft. Comput. 23, 7249–7262 (2019). https://doi.org/10.1007/s00500-018-3371-y
Liu, X., Ye, Q., Li, Y., Fan, J., Tao, Y.: Examining public concerns and attitudes toward unfair events involving elderly travelers during the COVID-19 pandemic using weibo data. Int. J. Environ. Res. Public. Health 18, 1756 (2021). https://doi.org/10.3390/ijerph18041756
Osorio-Arjona, J., Horak, J., Svoboda, R., García-Ruíz, Y.: Social media semantic perceptions on Madrid Metro system: using Twitter data to link complaints to space. Sustain Cities Soc. 64, 102530 (2021). https://doi.org/10.1016/j.scs.2020.102530
Paszto, V., Darena, F., Marek, L., Fuskova, D.: SGEM Spatial Analyses of Twitter Data – Case Studies, pp. 785–792 (2014)
Politis, I., Georgiadis, G., Kopsacheilis, A., Nikolaidou, A., Papaioannou, P.: Capturing twitter negativity pre- vs. mid-COVID-19 pandemic: an LDA application on london public transport system. Sustainability 13(23), 13356 (2021). https://doi.org/10.3390/su132313356
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24, 513–523 (1988). https://doi.org/10.1016/0306-4573(88)90021-0
Shalaby, A., Hosseini, M.: Linking social, semantic and sentiment analyses to support modeling transit customers’ satisfaction: towards formal study of opinion dynamics. Sustain Cities Soc. 49, 101578 (2019). https://doi.org/10.1016/j.scs.2019.101578
Vickerman, R.: Will Covid-19 put the public back in public transport? A UK perspective. Transp. Policy 103, 95–102 (2021). https://doi.org/10.1016/j.tranpol.2021.01.005
Wang, J., Dong, Y.: Measurement of text similarity: a survey. Information 11, 421 (2020). https://doi.org/10.3390/info11090421
Zajac, M., Horák, J., Osorio-Arjona, J., Kukuliač, P., Haworth, J.: Public transport tweets in London, Madrid and Prague in the COVID-19 period—temporal and spatial differences in activity topics. Sustainability 14, 17055 (2022). https://doi.org/10.3390/su142417055
Zhang, S., Feick, R.: Understanding public opinions from geosocial media. ISPRS Int. J. Geo.-Inf. 5, 74 (2016). https://doi.org/10.3390/ijgi5060074
Digital 2022: Czechia. In: DataReportal – Glob. Digit. Insights. https://datareportal.com/reports/digital-2022-czechia (2022). Accessed 22 Feb 2023
twitteR package – RDocumentation. https://www.rdocumentation.org/packages/twitteR/versions/1.1.9. Accessed 20 Nov 2022
Belly Mujinga’s death: Searching for the truth – BBC News. https://www.bbc.com/news/uk-54435703. Accessed 27 Feb 2023
Stratford station secures funding for plans set to relieve overcrowding. In: Rail Technol. Mag. https://www.railtechnologymagazine.com/articles/stratford-station-secures-funding-plans-set-relieve-overcrowding. Accessed 27 Feb 2023
Sadly the worst underground service in history – London Victoria Station, London Traveller Reviews. In: Tripadvisor. http://www.tripadvisor.co.uk/ShowUserReviews-g186338-d8388711-r575092501-London_Victoria_Station-London_England.html. Accessed 27 Feb 2023
Conversational AI platform & social listening tool – SentiOne. https://sentione.com/. Accessed 27 Feb 2023
Acknowledgements
This research was funded by the grant SP2023/023 of the Faculty of Mining and Geology of the Technical University of Ostrava “Possibilities of using artificial intelligence in geodata science for the purpose of predicting real estate prices” and grant “Podpora vědy a výzkumu v Moravskoslezském kraji 2022” of the Faculty of Mining and Geology of the Technical University of Ostrava.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zajac, M., Horak, J., Kukuliac, P. (2023). Semantic Analysis of Transit Related Tweets in London and Prague. In: Nguyen, N.T., et al. Advances in Computational Collective Intelligence. ICCCI 2023. Communications in Computer and Information Science, vol 1864. Springer, Cham. https://doi.org/10.1007/978-3-031-41774-0_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-41774-0_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41773-3
Online ISBN: 978-3-031-41774-0
eBook Packages: Computer ScienceComputer Science (R0)