BACKGROUND In recognition of the empowering potential of digital technologies, gender equality in internet access and digital skills is an important target in the United Nations (UN) Sustainable Development Goals (SDGs). Gender-disaggregated data on internet use are limited, particularly in less developed countries. OBJECTIVE We leverage anonymous, aggregate data on the online populations of Google and Facebook users available from their advertising platforms to fill existing data gaps and measure global digital gender inequality. METHODS We generate indicators of country-level gender gaps on Google and Facebook. Using these online indicators independently and in combination with offline development indicators, we build regression models to predict gender gaps in internet use and digital skills computed using available survey data from the International Telecommunications Union (ITU). RESULTS We find that women are significantly underrepresented in the online populations of Google and Facebook in South Asia and sub-Saharan Africa. These platform-specific gender gaps are a strong predictor that women lack internet access and basic digital skills in these populations. Comparing platforms, we find Facebook gender gap indicators perform better than Google indicators at predicting ITU internet use and low

No abstract

Boosting the number of women and girls entering careers involving STEM (Science, Technology, Engineering and Maths) is crucial to achieving gender equality, one of the UN Sustainable Development Goals. Girls and women tend to gravitate away from STEM fields at multiple stages from childhood through mid-career. The leaky pipeline is a metaphor often used to describe the loss of women in STEM and arguably other fields before reaching senior roles. Do interests expressed on social media mirror the leaky pipeline phenomenon? In this article, we collected advertisement data (reach estimates) from Facebook and Instagram disaggregated by US metros, age, gender, and interests related to STEM. We computed the Gender Gap Index (GGI) for each US metro and age group. We found that on Instagram, the GGIs for interest in Science decrease as users’ age increases, suggesting that relatively there is evidence that that women, compared to men, are losing interest in STEM at older ages. In particular, we find that on Instagram, there are plausible relative trends but implausible absolute levels. Nevertheless, is this enough to conclude that online data available from Instagram mirror the leaky pipeline phenomenon? To scrutinize this, we compared the GGIs for an interest in Science with the GGIs for placebo interests unrelated to STEM. We found that the GGIs for placebo interests follow similar age patterns as the GGIs for the interest in Science across US metros. Second, we attempted to control for the time spent on the platform by computing a usage intensity gender ratio based on the difference between daily and monthly active users. This analysis showed that the usage intensity gender ratio is higher among teenagers (13–17 years) than other older age groups, suggesting that teenage girls are more engaged on the platform that teenage boys. We hypothesize that usage intensity differences, rather than inherent interest changes, might create the illusion of a leaky pipeline. Despite the previously demonstrated value and huge potential of social media advertisement data to study social phenomena, we conclude that there is little evidence that this novel data source can measure the decline in interest in STEM for young women in the USA.

Wikipedia is the most influential popular information source on the Internet, and is ranked as the fifth most visited website [1] (Alexa, 2017). The English-language Wikipedia is a prominent source of online health information compared to other providers such as MedlinePlus and NHS Direct (Laurent and Vickers, 2009). Wikipedia has challenged the way that traditional medical encyclopaedia knowledge is built by creating an open sociotechnical environment that allows non-domain experts to contribute to its articles. Also, this sociotechnical environment allows bots – computer scripts that automatically handle repetitive and mundane tasks – to work with humans to develop, improve, maintain and contest information in Wikipedia articles. The contestation in Wikipedia is unavoidable as a consequence of its open nature, which means that it accepts contradictory views on a topic and involves controversies. The objective of this research is to understand the impact of controversy on the relationship between humans and bots in environments that are managed by the crowd. This study analyses all the articles under the WikiProject Medicine, and includes 36,850 Wikipedia articles. Medical articles and their editing history have been harvested from the Wikipedia API covering all edits from 2001 till 2016. The data includes the revisions ID, username, timestamp, and comment. The articles under the WikiProject Medicine contain 6,220,413 edits and around 1,285,936 human and bot editors. To measure controversies, we studied reverted and undone edits. A revert on Wikipedia occurs when an editor, whether human or bot, restores the article to an earlier version after another editor's contribution. Undone edits are reverted single edits from the history of a page, without simultaneously undoing all constructive changes that have been made since the previous edit. Reverted and undone edits that occur systematically indicate controversy and conflict (Tsvetkova et al., 2017). To measure the relationship between humans and bots, we focused on both positive and negative relationships. A positive relationship is when an editor, such as a human, endorses another editor, such as a bot, by reverting or undoing a recent edit to the other editor's contribution. A negative relationship is when an editor, such as human, discards another editor, such as a bot, by reverting or undoing the other editor's contribution. Our results show that there is a relationship between controversial articles and the development of a positive relationship between humans and bots. The results demonstrate that bots and humans could behave differently in controversial environments. The study highlights some of the important features of building health-related knowledge on Wikipedia. The contribution of this work is to build on previous theories that consider web-based systems as social machines. These theories recognise the joint contribution of humans and machines to activities on the web, but assume a very static type of relationships that is not sensitive to the environment in which humans and machines operate in. Understanding the interactions between humans and bots is crucial for designing crowdsourced environments that are integrative to their human and non-human population. We discuss how our findings can help set up future research directions and outline important implications for research on crowd. References: Laurent, M. R & Vickers, T. J (2009) ‘Seeking Health Information Online: Does Wikipedia Matter.?’ J Am Med Inform Assoc, 16(4), 471-479. Tsvetkova, M, García-Gavilanes, R, Floridi, L and Yasseri, T. (2017) ‘Even good bots fight: The case of Wikipedia.’ PLoS One, 12(2): e0171774. [1] https://www.alexa.com/topsites

No abstract