Tweets on the Go: Gender Differences in Transport Perception and Its Discussion on Social Media

Abstract

<jats:p>People often base their mobility decisions on subjective aspects of travel experience, such as time perception, space usage, and safety. It is well recognized that different groups within a population will react differently to the same trip, however, current data collection methods might not consider the multi dimensional aspects of travel perception, which could lead to overlooking the needs of large population groups. In this paper, we propose to measure several aspects of the travel experience from the social media platform Twitter, with a focus on differences with respect to gender. We analyzed more than 400,000 tweets from 100,000 users about transportation from Santiago, Chile. Our main findings show that both genders express themselves differently, as women write about their emotions regarding travel (both, positive and negative feelings), that men express themselves using slang, making it difficult to interpret emotion. The strongest difference is related to harassment, not only on transportation, but also on the public space. Since these aspects are usually omitted from travel surveys, our work provides evidence on how Twitter allows the measurement of aspects of the transportation system in a city that have been studied in qualitative terms, complementing surveys with emotional and safety aspects that are as relevant as those traditionally measured.</jats:p>

A Framework to Understand Attitudes towards Immigration through Twitter

“…These aspects include multiple emotions and other topical dimensions of expression, which may be compared between attitudes. LIWC usage with social media data includes identifying health issues [59,60], predicting political sentiment [61], and understanding perception about the transportation experience [62]. The Spanish version has been validated experimentally [63], enabling its consideration in our work.…”

Drake or Hen? Machine Learning for Gender Identification on Twitter

“…Social networks provide a rich amount of real time data that social scientists analyze to find actionable insights. For instance [3] investigates Chilean citizens perception of transport, [4] looks at how social media influenced the 2016 presidential campaign in the United States or [5] focuses on emotions and narratives with respect to gender. The inherent bias carried by social networks illustrates the need to identify gender for social scientists when analyzing the networks before drawing any assumption or conclusion.…”

“…Besides, the community has focused mainly a lot on the Twitter data. For instance [3,5,6,7,8,9,10,11] based their research only on tweets and did not address other social networks. As argued by Steinert-Threlkeld [12]: "Twitter presents an ideal combination of size, international reach, and data accessibility that make it the preferred platform in academic studies".…”

“…Among them, we highlight Demographer [22,23] and [24]. Other works [3] tackle the problem with classical machine learning techniques converting names, description and/or username in a bag-of-words representation through word or character n-grams. We also see a development of gender identification through deep-learning methods, for instance [8,9] added a computer vision component to process the user profile picture to improve results.…”

“…One of the main difficulties is to build one model dealing with several languages at the same time, a lot of works [3,4,5,6,10,22,7] focused on one or two languages only. Wang et al [9] are the first ones to tackle the problem in a multilingual paradigm, processing 32 different languages.…”