Estimating Telecommuting Rates in the USA Using Twitter Sentiment Analysis

被引：0
作者：
Juan Acosta-Sequeda [1 ]
Motahare Mohammadi [1 ]
Sarthak Patipati [1 ]
Abolfazl Mohammadian [1 ]
Sybil Derrible [1 ]
机构：
[1] University of Illinois Chicago, 1200 W Harrison St, Chicago, 60607, IL
来源：
Data Science for Transportation | 2024年 / 6卷 / 3期
关键词：
COVID-19; Sentiment analysis; Telecommuting; Time series analysis; Work from home;
D O I：
10.1007/s42421-024-00114-0
中图分类号：
学科分类号：
摘要：
The COVID-19 pandemic had a significant impact on virtually every human activity. Millions of workers around the globe from eligible professions stayed at home working as part of the measures taken to contain the virus’ spread. The change in transportation demand associated with this phenomenon poses a challenge for cities, especially regarding public transportation, where the decrease in demand arose critical questions on how to assess decreased ridership and potential rebound effects. Given that social media is a virtual space where people often report their opinions and intentions, we believe such data can be used to gather aggregated measures of human behavior. Hence, we ask: can we obtain real-time demand change estimates using social media data? Hence, the aim of this work is to take social media unstructured information and transform it into structured insights that can offer almost real-time estimates on demand trends associated with telecommuting. To achieve this, we obtained around 50,000 geo-tagged tweets over a 2 year period relevant to telecommuting in the USA. With that, we leveraged Transformers machine learning methods to fine-tune a language model capable of automatically assigning a sentiment to tweets on this topic. We used the time evolution of the obtained sentiments as covariates in time series forecasting models to estimate telecommuting rates at both the national and state levels, observing a drastic improvement over the estimates without such covariates. Our major finding indicates that it is possible to structure social media data to use it to obtain demand change estimates, and that the accuracy of such estimates depends heavily on how much people discuss the topic in question in a determined geography. This finding is in line with others that have found alternative ways of obtaining insights on transportation data, and hence is a relevant contribution toward real-time data-driven approaches for transportation demand assessment. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.
引用
收藏
相关论文
共 65 条
  • [1] Acosta-Sequeda J., Derrible S., GTdownloader: a python package to download, visualize, and export georeferenced tweets from the Twitter API, J Open Res Softw, (2023)
  • [2] Agarwal A., Jasneet S., End-to-end sentiment analysis of Twitter data, Proceedings of the workshop on information extraction and entity analytics on social media data. The COLING 2012 Organizing Committee, pp. 39-44, (2012)
  • [3] Aisopos F., George P., Theodora V., Sentiment analysis of social media content using N-gram graphs, Proceedings of the 3rd ACM SIGMM international workshop on social media. WSM ’11, pp. 9-14, (2011)
  • [4] Aston N., Liddle J., Wei H., Twitter sentiment in data streams with perceptron, J Comput Commun, (2014)
  • [5] Bakliwal A., Piyush A., Senthil M., Nikhil K., Mukesh S., Vasudeva V., Mining sentiments from Tweets, Proc. of the 3rd workshop in computational approaches to subjectivity and sentiment analysis, (2012)
  • [6] Balabantaray R.C., Mohd M., Sharma N., Multi-class twitter emotion classification: a new approach, Int J Appl Inf Syst, 4, September, pp. 48-53, (2012)
  • [7] Balbontin C., Hensher D.A., Beck M.J., Advanced modelling of commuter choice model and work from home during COVID-19 restrictions in Australia, Transp Res Part E: Logist Transp Rev, 162, June, (2022)
  • [8] Barbosa L., Junlan F., Robust sentiment detection on twitter from biased and noisy data, Coling 2010: Posters. Coling, 2010, pp. 36-44, (2010)
  • [9] Beck M.J., Hensher D.A., Working from home in Australia in 2020: positives, negatives and the potential for future benefits to transport and society, Transp Res Part a: Policy Pract, 158, April, pp. 271-284, (2022)
  • [10] Bollen J., Mao H., Zeng X., Twitter mood predicts the stock market, J Comput Sci, 2, 1, pp. 1-8, (2011)
1234567