The geography of sentiment towards the Women’s March of 2017

Abstract

The Women's March of 2017 generated unprecedented levels of participation in the largest, single day, protest in history to date. The marchers protested the election of President Donald Trump and rallied in support of several civil issues such as women's rights. "Sister marches" evolved in at least 680 locations across the United States. Both positive and negative reactions to the March found their way into social media, with criticism stemming from certain, conservative, political sources and other groups. In this study, we investigate the extent to which this notable, historic event influenced sentiment on Twitter, and the degree to which responses differed by geographic area within the continental U.S. Tweets about the event rose to an impressive peak of over 12% of all geo-located tweets by midday of the March, Jan. 21. Messages included in tweets associated with the March tended to be positive in sentiment, on average, with a mean of 0.34 and a median of 0.07 on a scale of-4 to +4. In fact, tweets associated with the March were more positive than all other geo-located tweets during the day of the March. Exceptions to this pattern of positive sentiment occurred only in seven metropolitan areas, most of which involved very small numbers of tweets. Little evidence surfaced of extensive patterns of negative, aggressive messages towards the event in this set of tweets. Given the widespread nature of online harassment and sexist tweets, more generally, the results are notable. In sum, online reactions to the March on this social media platform suggest that this modern arm of the Women's Movement received considerable, virtual support across the country.

Can Social Media Anti-abuse Policies Work? A Quasi-experimental Study of Online Sexist and Racist Slurs

“…We develop a classifier that we apply to the sentiment analysis of the content of the entire tweet message, which includes one of the two key words (Felmlee, Blanford et al 2020; Felmlee, Inara Rodis et al 2020; Zhang and Felmlee 2017). The sentiment tool is a variation of the VADER (Valence Aware Dictionary and Sentiment Reasoner) classifier.…”

“…Prior research finds that it takes an average of 24 seconds to 1.5 minutes to locate the first of thousands of derogatory, aggressive tweets, on the basis of a sample of searches for assorted defamatory slurs and insults (e.g., n**ger , who*e , fa**ot ) (Sterner and Felmlee 2017). Additional research on sexist tweets identified more than 419,000 tweets per day that included at least one of four sexist slur words ( bi*ch , c**t , s**t , and who*e ) during a one-week collection period (Felmlee et al 2020). Such negative messages often can be retweeted or “liked” by followers, thereby creating networks of cyberbullying that spread far beyond the original perpetrator and target (Felmlee et al 2018).…”

“…To address this question, we begin by locating tweets that include a gendered slur, bi!ch , during the month prior to and following the effective date of the most widely publicized of Twitter’s recent rule implementations (December 18, 2017). Previous research finds that bi!ch is a particularly common slur used to demean a feminine target on Twitter (Felmlee et al 2020), and it is one of the four most prevalent curse words on the platform (Wang et al 2014).…”

Linking Geosocial Sensing with the Socio-Demographic Fabric of Smart Cities

“…Other research [37] even found a partly negative correlation between happiness and health, i.e., the happier, the unhealthier. At the scale of entire cities, [38] conducted a massive study on the relationship between "Twitter happiness" and demographic and place characteristics, and [39] investigated nation-wide sentiments towards a historic event (Women's March 2017).…”

#AllforJan: How Twitter Users in Europe Reacted to the Murder of Ján Kuciak—Revealing Spatiotemporal Patterns through Sentiment Analysis and Topic Modeling

“…Moreover, the widespread and well-established advantages of network modeling approaches on hashtags [13,14,28,29] or users [30,31] in recent literature analyzing protests based social media data, they are often not capable of handling the complexity of the sentiment, temporal, and spatial patterns of these actions in one approach. One limitation is that the analysis relies on Tweets having coordinates as an inherent part of the dataset [32,33], which-according to earlier studies-represents only a small subset of all tweets (approximately 1-10%) posted within a specified time period [34]. Another limitation is that they focus only on a single language (usually English) that may also limit the spatial interpretability of the results [35], especially in the case of movements that span over multiple countries.…”