Use of social media for assessing sustainable urban mobility indicators

Abstract

Achieving sustainable urban mobility is a complex and multivariate issue that requires constant monitoring and evaluation of the existing situation and possible reconsideration and adjustment of objectives and strategy. The use of indicators is perhaps the most common methodological assessment tool for the sustainable urban mobility level achieved. Key performance indicators can provide in a simple way useful information for complex phenomena in an urban area (i.e. identification of the specific problems and their development over time). Thus, they contribute at a great degree to the decisions made concerning the prioritization of measures and policies toward achieving a goal. However, the use of indicators often constitutes a highly time consuming and costly process due to the large volumes of raw data required for their calculation. In recent years, a solution toward this problem is attempted to be given through the adoption of new technologies and approaches, such as the collection and export of 'big data' from social networks such as Facebook, Twitter, etc. Social networks provide to their users a continuous and enhanced ability for communication, interface and interaction. Such networks are therefore an important potential tool for the promotion of research in the transport sector, as the amount of data generated in their context gives the possibility to analyse and investigate with greater precision critical issues (e.g. trips characteristics) of urban mobility. The present study is an attempt to link the indicators related to sustainable mobility with social networks. The main advantage resulting from the above link, beyond the possibility of a more precise evaluation of the indicators, is to highlight the society's position toward the prioritization of the various transport-related aspects and measures.

Urban sprawl and its impact on sustainable urban development: a combination of remote sensing and social media data

“…According to (Gislason, Benediktsson, and Sveinsson 2006) and (Ming et al 2016), the Random Forest (RF) algorithm exhibits good robustness compared with other traditional methods in the classification of a remote sensing image because it requires fewer parameters, minimal manual intervention, and yields high classification accuracy, can also manage high-dimensional data and obtain classification results rapidly. This explains the adoption of RF in land cover classification using multispectral and hyperspectral satellite sensor imagery as shown in studies by (Ghimire, Rogan, and Miller 2010;Gislason, Benediktsson, and Sveinsson 2006;Nitze, Barrett, and Cawkwell 2015;Rodriguez-galiano et al 2012) and data platforms and mapping such as LIDAR and radar image classifications, lithological mapping, as well as mineral prospectively prediction.…”

“…This information is useful for activity pattern analysis as shown by (Dangermond and Goodchild 2020;Kainz 2020;Monsivais et al 2017). Other studies in urban areas have utilized social media data and satellite imagery to gain insights on situational awareness of human activities Stefanidis et al 2011), urban land use mapping (Hu et al 2016); service-oriented architecture applications (Pashova and Bandrova 2017) spatiotemporal analysis in the urban environment impacted by human activities (Monsivais et al 2017;Sumari et al 2019b); and, determination of users' locations, tweets, and home area from Twitter data to understand the patterns of social media usage (Hu et al 2019;Lee et al 2014;Sdoukopoulos et al 2018;Tsou et al 2015;Weiler, Grossniklaus, and Scholl 2016; Zhou and Zhang 2016).…”

Urban transportation sustainability assessments: a systematic review of literature

“…This miscellaneous group includes four articles that combine MCDA and modelling as their main methods to assess policies and plans. Other papers include a study of accessibility in relation to travel modes and behaviour using a place rank method (Vega, 2012) and a study of citizen perceptions using social media data mining and sentiment analysis (Sdoukopoulos, Nikolaidou, Pitsiava-Latinopoulou, & Papaioannou, 2018).…”

“…A general satisfaction with the transportation system and service is most commonly applied. In particular, Olofsson et al (2016), Toth-Szabo and Varhelyi (2012), and Sdoukopoulos et al (2018) extensively apply the citizen satisfaction and perception aspects as related to, for example, congestion, noise disturbance, or public transportation reliability.…”

“…All papers apply a system-level approach to transportation modes and include the urban area as a whole, except for Machler and Golub (2012) who focus on a single low-income neighbourhood. Additionally, Sdoukopoulos et al (2018) position their evaluation of citizen perceptions towards new suitable indicators and the use of social media and big data in transportation assessments. As expected, this group shows a concentration of participatory data collection methods.…”