Comparison of Emoji Use in Names, Profiles, and Tweets

In most of our work to date with respect to exploring social media, we have only looked at the text or images from online social media platforms (e.g. Twitter and Flickr) and excluded  emojis from the analysis. However, this has now changed with a new paper co-authored with  Melanie Swartz entitled "Comparison of Emoji Use in Names, Profiles, and Tweets" which will be presented at he Eighth IEEE International Workshop on Semantic Computing for Social Networks and Organization Sciences in conjunction with 14th IEEE International Conference on Semantic Computing. 

In the paper we discuss how emoji use is becoming more and more popular by users of online social networking sites as they can be an effective way to express sentiment, sarcasm or feelings which are not easily conveyed as text. However, limited research has focused on analysis of the behavior of emoji use or how to compare emoji use across users or documents. To overcome this limitation, in this paper: (1) we present a methodology to extract, aggregate, and compare emoji use across a collection of documents based on Unicode emoji category and subcategories, (2) we present a baseline of statistics of emoji use in user names, profile descriptions, and tweets, and (3) we compare emoji use as categories and subcategories between users and content a user shares in the user name, profile description, retweets and non-retweets.

By considering this semantic grouping of emojis, we move the research on emojis beyond just comparing individual emojis and broad aggregations. In applying our methodology to a set of 44 million tweets and over 3 million user profiles, we find that differences in emoji use emerged based on document type (i.e., user names, profile descriptions, retweets, and non-retweets). As such, our work offers a new lens to study and compare forms of self expression across a variety of digital media content types. If you wish to find out more about this work, below we present the abstract to the paper, our workflow that allows for emoji comparison and some results. Finally at the bottom of the page we provide the full reference and a link to the paper.

Abstract 

Online social networking applications are popular venues for self-expression, communication, and building connections between users. One method of expression is that of emojis, which is becoming more prevalent in online social networking platforms. As emoji use has grown over the last decade, differences in emoji usage by individuals and the way they are used in communication is still relatively unknown. This paper fills this gap by comparing emoji use across users and collectively in user names, profiles, and in original and re-shared content. We present a methodology that enables comparison of semantically similar emojis based on Unicode emoji categories and subcategories. We apply this methodology to a corpus of over 44 million tweets and associated user names and profiles to establish a baseline which reveals differences in emoji use in user names, profile descriptions, non-retweets, and retweets. In addition, our analysis reveals emoji super users who have a significantly higher proportion and diversity of emoji use. Our methodology offers a novel approach for summarizing emoji use and enables systematic comparison of emojis across individual user profiles and communication patterns, thus expanding methods for semantic analysis of social media data beyond just text.

Keywords: emoji; social media analytics; content analysis; online social networks.

Workflow for emoji comparison.

Proportion of emoji use in profiles, names, retweets, and non-retweets, ordered by category.

Proportion of emoji use by subcategory.

Top emoji for each communication type.

Reference:

Swartz, M. and Crooks, A.T. (2020), Comparison of Emoji Use in Names, Profiles, and Tweets, The Eighth IEEE International Workshop on Semantic Computing for Social Networks and Organization Sciences: From User Information to Social Knowledge, San Diego, CA. (pdf)

New Paper: Insights into Human-wildlife Interactions in Cities from Bird Sightings Recorded Online

In the past we have explored how social media can be used to delineate earthquakes, locate wildfires or be used to understand urban morphology. However, recently we have also started to explore how social media and crowdsourced data can be utilized to to study socio-environmental systems. Keeping with this them, Bianca Lopez, Emily Minor, and myself have recently had a paper published in Landscape and Urban Planning entitled "Insights into Human-wildlife Interactions in Cities from Bird Sightings Recorded Online."  

In the paper we explore where do people observe birds, using the city of Chicago as our case study. By utilizing urban bird observations collected from eBird, iNaturalist, and Flickr we find that most bird observations occurred in open space zoned for recreational use. Further analysis revealed that the number of bird observations varied with income, population size, and proximity to Lake Michigan. If you want to find out more, below is the abstract to the paper, along with some figures of the results and at the bottom of the post, the full reference and a link to the paper. 

Abstract:

Interactions with nature can improve the wellbeing of urban residents and increase their interest in biodiversity. Many places within cities offer opportunities for people to interact with wildlife, including open space and residential yards and gardens, but little is known about which places within a city people use to observe wildlife. In this study, we used publicly available spatial data on people’s observations of birds from three online platforms—eBird, iNaturalist, and Flickr—to determine where people observe birds within the city of Chicago, Illinois (USA). Specifically, we investigated whether land use or neighborhood demographics explained where people observe birds. We expected that more observations would occur in open spaces, and especially conservation areas, than land uses where people tend to spend more time, but biodiversity is often lower (e.g., residential land). We also expected that more populated neighborhoods and those with higher median age and income of residents would have more bird observations recorded online. We found that bird observations occurred more often in open spaces than in residential areas, with high proportions of observations in recreation areas. In addition, a linear regression model showed that neighborhoods with higher median incomes, those with larger populations, and those located closer to Lake Michigan had more bird observations recorded online. These results have implications for conservation and environmental education efforts in Chicago and demonstrate the potential for social media and citizen science data to provide insight into urban human-wildlife interactions.

Keywords: Urban biodiversity, human-nature interaction, open space, residential, spatial analysis, birdwatching.

Map of bird observations from the three web platforms (Flickr, eBird, and iNaturalist) across the city of Chicago, in relation to mean median income of community areas (left panel) and open space, residential land use, highways, and waterways (right panel).

Proportions of observations recorded in different land uses on the three different online platforms (n = 7944 eBird; n = 474 iNaturalist; n = 561 Flickr). There was a significant difference between the three distributions (simulated p-value less than 0.001), including in the proportions of observations in conservation, recreation, and residential land uses.

Full Reference:

Lopez, B.E., Minor, E.S. and Crooks, A.T. (2020), Insights into Human-wildlife Interactions in Cities from Bird Sightings Recorded Online, Landscape and Urban Planning. 196: 103742. (pdf)

Models from Teaching CSS Fall 2019

Avid readers of this blog (if there are any) may be familiar with my routine of combing end of semester projects into a short movie and blogging about it. Well its that time again. Last semester I gave a class entitled Introduction to Computational Social Science and instead of setting a final exam, I ask the students to carryout an end of semester research project. The aim of this exercise is to cement what the students have (hopefully) learnt during the semester. I.e.: 

• to understand the motivation for the use of computational models in social science theory and research; 
• to learn about the variety of CSS research programs across the social science disciplines; 
• to understand the distinct contribution that CSS can make by providing specific insights about society, social phenomena at multiple scales, and the nature of social complexity.

Below you can see some of the outputs from these projects this last fall. These models ranged in type from agent-based models, microsimulation to system dynamics models applied to a variety of topics from how machine learning can be utilized within agent-based models to applications such as the courts, common pool resources, public goods, economic growth, supply chains, heath care issues (e.g. patient diagnosis, fungi infections within hospitals), team performance, labor markets, voting, and several other topics along the way.

New Working Paper: Agent-Based Models for Geographical Systems: A Review

Its been a while since we published a working paper, especially a CASA one, but this has now changed with the release of a new one entitled "Agent-Based Models for Geographical Systems: A Review." In the paper Alison Heppenstall, Nick Malleson, Ed Manley, Jiaqi Ge, Michael Batty and myself reflect back on the agent-based modeling and their use in geographical systems. 

In the paper we revisit challenges that we first explored back in 2008 (which an earlier version was another CASA working paper) and progress that has been made to address them. We then  explore new challenges within the field of agent-based models especially in light of new new (big) data along with new opportunities (such as data assimilation). If you want to find out more about the paper, below is the abstract and a ling to the paper.

Abstract:

This paper charts the progress made since agent-based models (ABMs) of geographical systems emerged from more aggregative approaches to spatial modeling in the early 1990s. We first set the context by noting that ABM explicitly represent the spatial system by individual objects, usually people in the social science domain, with behaviors that we simulate here mainly as decisions about location and movement. Key issues pertaining to the way in which temporal dynamics characterize these models are noted and we then pick up the challenges from the review of this field conducted by Crooks, et al. (2008) some 12 years ago which was also published as a CASA working paper. We then define key issues from this past review as pertaining to a series of questions involving: the rationale for modeling; the way in which theory guides models and vice versa; how models can be compared; questions of model replication,experiment, verification and validation; how dynamics are incorporated in models; how agent behaviors can be simulated; how such ABMs are communicated and disseminated; and finally the data challenges that still dominate the field. This takes us to the current challenges emerging from this discussion. Big data, the way it is generated, and its relevance for ABM is explored with some important caveats as to the relevance of such data for these models, the way these models might be integrated with one another and with different genera of models are noted, while new ways of testing such models through ensemble forecasting and data assimilation are described. The notion about how we model human behaviors through agents learning in complex environment is presented and this then suggests that ABM still have enormous promise for effective simulations of how spatial systems evolve and change.

Full Reference:

Heppenstall, A., Crooks, A.T., Malleson, N., Manley, E., Ge J. and Batty, M. (2019), Agent-Based Models for Geographical Systems: A Review. Centre for Advanced Spatial Analysis (University College London): Working Paper 214, London, England. (pdf)

Bots Fired: Examining Social Bot Evidence in Online Mass Shooting Conversations

Building upon our work with respect to how bots impact online conversations pertaining to global events and  health,  we have extended this research to see what role bots play in mass shooting events. In our new paper published in Palgrave Communications entitled "Bots Fired: Examining Social Bot Evidence in Online Mass Shooting Conversations" we examine four mass shooting events (i.e., Las Vegas, Sutherland Springs, Parkland, and Santa Fe) and find that social bots participate and contribute to online mass shooting conversations in a manner that is distinguishable from human contributions. Below we provide the abstract, along with some figures from the paper that highlight our methodology and main results. Finally at the bottom of the post, we provide the full reference to the paper. 

Abstract:

Mass shootings, like other extreme events, have long garnered public curiosity and, in turn, significant media coverage. The media framing, or topic focus, of mass shooting events typically evolves over time from details of the actual shooting to discussions of potential policy changes (e.g., gun control, mental health). Such media coverage has been historically provided through traditional media sources such as print, television, and radio, but the advent of online social networks (OSNs) has introduced a new platform for accessing, producing, and distributing information about such extreme events. The ease and convenience of OSN usage for information within society’s larger growing reliance upon digital technologies introduces potential unforeseen risks. Social bots, or automated software agents, are one such risk, as they can serve to amplify or distort potential narratives associated with extreme events such as mass shootings. In this paper, we seek to determine the prevalence and relative importance of social bots participating in OSN conversations following mass shooting events using an ensemble of quantitative techniques. Specifically, we examine a corpus of more than 46 million tweets produced by 11.7 million unique Twitter accounts within OSN conversations discussing four major mass shooting events: the 2017 Las Vegas concert shooting, the 2017 Sutherland Springs church shooting, the 2018 Parkland school shooting and the 2018 Santa Fe school shooting. This study’s results show that social bots participate in and contribute to online mass shooting conversations in a manner that is distinguishable from human contributions. Furthermore, while social bots accounted for fewer than 1% of total corpus user contributors, social network analysis centrality measures identified many bots with significant prominence in the conversation networks, densely occupying many of the highest eigenvector and out-degree centrality measure rankings, to include 82% of the top-100 eigenvector values of the Las Vegas retweet network.

Keywords: Social bots, mass shootings, school shootings, online social networks, computational social science.

 Overview of social bot analysis framework illustrating methodological steps taken to analyze social bots within online social network conversations involving mass shooting events

Overall tweet corpus volumes and suspected social bot contributions for each associated OSN mass shooting 215 event conversation.

Intra-group and cross-group retweet interaction rates among and between human (blue) and suspected social bot (red) user accounts for a one-month period following the (a) Las Vegas, (b) Sutherland Springs, (c) Parkland and (d) Santa Fe shooting events.

Social bot accounts in the top-N, where N = 1000/100/10, (a) eigenvector, (b) in-degree, (c) out-degree and (d) PageRank centrality measurement rankings within OSN mass shooting retweet networks discussing the Las Vegas (red), Sutherland Springs (green), Parkland (blue) and Santa Fe (purple) shooting events.

Full Reference:

Schuchard, R., Crooks, A.T., Croitoru, A. and Stefanidis, A. (2019) Bots Fired: Examining Social Bot Evidence in Online Mass Shooting Conversations, Palgrave Communications, 5: 158. Available at https://doi.org/10.1057/s41599-019-0359-x. (pdf)