Investigating the Emotional Responses of Individuals to Urban Green Space Using Twitter Data: A Critical Comparison of Three Different Methods of Sentiment Analysis

Abstract

In urban research, Twitter data have the potential to provide additional information about urban citizens, their activities, mobility patterns and emotion. Extracting the sentiment present in tweets is increasingly recognised as a valuable approach to gathering information on the mood, opinion and emotional responses of individuals in a variety of contexts. This article evaluates the potential of deriving emotional responses of individuals while they experience and interact with urban green space. A corpus of over 10,000 tweets relating to 60 urban green spaces in Birmingham, United Kingdom was analysed for positivity, negativity and specific emotions, using manual, semi-automated and automated methods of sentiment analysis and the outputs of each method compared. Similar numbers of tweets were annotated as positive/neutral/negative by all three methods; however, inter-method consistency in tweet assignment between the methods was low. A comparison of all three methods on the same corpus of tweets, using character emojis as an additional quality control, identifies a number of limitations associated with each approach. The results presented have implications for urban planners in terms of the choices available to identify and analyse the sentiment present in tweets, and the importance of choosing the most appropriate method. Future attempts to develop more reliable and accurate algorithms of sentiment analysis are needed and should focus on semi-automated methods.

Exploring the smart-natural city interface; re-imagining and re-integrating urban planning and governance

“…By their simultaneous use, together the 5 characteristics of the Smart-Natural city interface have the potential to help start dialogues to resolve concerns (Arts et al, 2015;Roberts, 2017) over how these benefits are transferred to and received by urban populations and the circumstances under which this can happen most effectively. The use of this new approach can guard against widening the digital divide and amplifying poverty gaps as described by Hernandez & Roberts (2018), allows us to 'see the expertise of citizens' (Noveck, 2015) and so address the disconnect challenge identified by Colding & Barthel (2017).…”

“…New digital techniques for informing better decisions are not yet systemic but are emerging and Arts et al 2015have identified a number of categories of data alongside risks and problems that accompany digital conservation. Others have identified specific applications for urban landscapes, remote and human sensing (see for example; Blaschke et al, 2011;Hill, 2016;IWUN, 2017;Roberts et al, 2018;Seresinhe et al, 2017 andTu et al, 2018). Carton & Ache (2017) have specifically explored the rise of citizen-sensor-networks, combining civic engagement and ICT.…”

Revisiting the Role of Place in Geographic Information Science

“…Many applications use the output of latent semantic analysis (LSA) from a-typically online-text corpus and utilize semantic, semiotic, and linguistic analysis (e.g., [91][92][93][94]). In fact, those methods are increasingly used to gather information on the mood, opinion, and emotional responses of individuals in a variety of contexts, namely space, time, and situation-specific (only applicable for this situation) context (e.g., [77,95,96]). Various recent studies using social media, particularly Twitter data, aim to reveal a sense of place.…”

“…Various recent studies using social media, particularly Twitter data, aim to reveal a sense of place. While many computer scientists and computer linguists, on the other hand, discover the power of spatial concepts [95,[97][98][99][100][101][102][103], and likewise, GIScientists discover the potential of semantic analyses [77,94,96,[104][105][106], the dividing line between spatial and non-spatial applications diminishes.…”

Multi-class twitter data categorization and geocoding with a novel computing framework

“…Twitter data are used for assessing various events (D'Andrea et al, 2015;Gu et al, 2016;He, Boas, Mol, & Lu, 2017;Purohit et al, 2014;Qian, 2016;Roberts et al, 2018;Tang et al, 2017) including natural disasters, mass emergency, acts of terrorism, extreme weather events, political protests, and transportation events. In a study conducted by Mirończuk and Protasiewicz (2018), the authors have reviewed recent research to understand the general approach of text classification practices and identify the future research questions related to text classification (Mirończuk & Protasiewicz, 2018).…”