Online Collective Action

Sentiment Analysis deals with the detection and analysis of affective content in written text. It utilizes methodologies, theories, and techniques from a diverse set of scientific domains, ranging from psychology and sociology to natural language processing and machine learning. In this chapter, we discuss the contributions of the field in social media analysis with a particular focus in online collective actions; as these actions are typically motivated and driven by intense emotional states (e.g., anger), sentiment analysis can provide unique insights into the inner workings of such phenomena throughout their life cycle. We also present the state of the art in the field and describe some of its contributions into understanding online collective behavior. Lastly, we discuss significant real-world datasets that have been successfully utilized in research and are available for scientific purposes and also present a diverse set of available tools for conducting sentiment analysis.

The rapidly growing online activities in the Web motivate us to analyze the reactions of different emotional catalysts on various social networking substrates. Thus, in the present chapter, different concepts, motivations, approaches and applications of emotion analysis are discussed in order to achieve the main challenging tasks such as feature representation schema, emotion classification, holder and topic detection and identifying their co-references, etc. as these are the main salient points to cover while analyzing emotions in social media. Additionally, a prototype is also described and assessed to analyze emotions, its collective actions based on users and topics, its components and their association from different available data sets of English and Bengali as case studies. Experiments and final outcomes highlight the promise of the approach and some open research problems.

Social media is growing at substantially faster rates, with millions of people across the globe generating, sharing and referring content on a scale apparently impossible a few years back. This has cumulated in huge participation with plenty of updates, opinions, news, blogs, comments and product reviews being constantly posted and churned in social Websites such as Facebook, Digg and Twitter to name a few. Even the events that are offline fetch the attention of social crowds, and considerably, their rapid sharing of views could signify the sentiment and emotional state of crowds at that particular instance. In the recent past, social media during terrorist strikes or natural disasters or in panic situations exhibits a tremendous impact in propagating messages among different communities and people. But the crowd participation in these interactions is grouped on the fly, and once the events fade out, they slowly disappear from the social media. We continuously iterate the challenges of identifying the behavioral pattern of the so-called transient crowd and their dispersion or convergence of sentiment and broadly answer how that could tell upon the offline events as well. While modeling the dynamics of such crowds, relevant clustering techniques have been consulted, although any method alone was not found compatible with the social media setup. The continuous cognitive pattern like a homophilic or curious and intuitive crowd with vector attributes on such social interaction motivates to incorporate an ant’s or swarm’s colonial behavior. Ants and swarms demonstrate well-defined chemical communication signals known as pheromones to segregate and distinguish specific communication patterns from cells of high concentration to those of low concentration. Hence, the positive and negative sentiment of transient crowds could be modeled, and the local influence can be measured on their posts through pheromone modeling and reinforcement of the shortest path of an ant or swarm’s life cycle. The primary objective of the chapter is to introduce a comparative smart methodology of ants and swarms as agent-based paradigms for investigating the community identification, namely, for Facebook and Twitter. The social media platforms are large enough to accommodate the ant and swarm graph for a pheromone model, tuning the time complexity of pheromone deposition and evaporation. Subsequently, the strength of association between transient users also could vary in terms of edge distribution and decay over stochastic measures of social events. We inculcate a couple of test cases fetched from Facebook on recent terror strikes of Mumbai, India, modeled using ants’ and swarms’ behavior. The results are encouraging and still in process. Empirically, the flow of sentiment and the corresponding dispersion of the crowd effect should infer or ignore a particular event, will leave a socio-computational benchmark for the mentioned proposition and will assist the ant alive in the system to reciprocate.

This chapter analyzes patterns in messages posted to several Internet discussion forums from the perspective of the sentiment expressed in them and the collective character of observed emotions. A large set of records describing comments expressed in diverse cyber communities—blogs, forums, IRC channels, and the Digg community—was collected, and sentiment classifiers were used to estimate the emotional valence (positive, negative, or neutral) of each message. A comparison with simple models showed that the data included clusters of comments with the same emotional valence that were much longer than similar clusters created by a random process. This shows that there are emotional interactions between participants so that future posts tend to have the same valence as previous posts. Threads starting from a larger number of negative comments also last longer so negative emotions can be treated as a kind of discussion fuel; when the fuel (negativity) is used up in the discussion, it may finish. Moreover, the amount of user activity in a particular thread correlates positively with the presence of negative emotions expressed by the individual user in the thread. In summary, the analyses describe individual and collective patterns of emotional activities of Web forum users and suggest that negativity is needed to fuel important discussions.

There is a growing number of opportunities for users to perform collective actions in social networks: Such collective actions engage users in correspondents social interactions. Although some models for representing users and their relationships in social networks have been proposed, to the best of our knowledge, these models do not explain what the underlying social interactions are. In previous work, we have proposed a human-readable technique for modeling and measuring social interactions, which resulted from users’ actions that involved, for instance, media types, interaction devices, and viral content. In our technique, social interactions are represented as behavioral contingencies in the form of if-then rules, which are then measured using an established data mining procedure. After being able to represent and measure a variety of social interactions, we identified the opportunity of transforming our technique into a method for capturing, representing, and measuring collective actions in social networks. In this chapter, we present our method and detail how it was applied to represent and measure social interactions among a group of 1,600 Facebook users over the period of 7 months. Our results report the link among actions (e.g., like), media objects (e.g., photo), application type (Web or mobile), and device type (e.g., Android).

This research addresses the question of whether the rise of blogs as a rich information source may create new opinion leaders that transform and challenge the traditionally held public views on drugs and European health care. We investigate blogs that discuss issues related to European health care and European pharmaceuticals for a selected 6 month period. In our approach of the blog space, we take a sociological perspective and design a multistage methodology for data collection and data analysis that differs from the traditionally used crawling techniques by computer scientists.

The results reveal that in spite of the high volume of blogs for the investigated period, only a small number are interlinked by mutual referrals. The emerging network configuration is represented by a small core component with a large number of dyads, or short tails, which represents a fragmented community space. Our content analysis reveals that the information broadcasted in blogs shows emerging semantic differentiation related to specific health issues and disease categories. Our findings support the conclusion that in spite of the high technical Internet connectivity facilitated by search engines and Internet crawling tools, community interaction is limited, and there is no evidence of online crowd or collective action.

VirtualVirtual citizen science creates Internet-based projects that involve volunteers who collaborate with scientists in authentic scientific research. Forms of computer-mediated communication like websites, email, and forums are integral for all project activity and interaction between participants. However, the specific forms of computer-mediated communication vary because of the functionalities they must serve for a particular virtual citizen science project. After illustrating how computer-mediated communication is used by the Zooniverse, a collection of successful virtual citizen science projects, this chapter describes how virtual citizen science can be understood as a form of online collective action that takes place in the context of conducting scientific research. Using collective action theory allows for the creation of a collective action space that can be used to compare particular project features or entire projects based on a combination of the forms of interaction and project responsibilities available to volunteers.

The social Web has changed the nature of human collaboration with new possibilities for massive-scale cooperation in such important endeavors as scientific research and environmentally important collective action. While first generation citizen science projects have successfully used the Web to crowd-source environmental data collection, “next generation” citizen science practice networks combine crowd-sourcing, joint sense of purpose, and soft institutional governance with the distributed intelligence and efficacy of online social networks. Here we tap into evolutionary theory and social psychology to generate hypotheses for how such “next generation” citizen projects can best support pro-environmental behaviors like habitat restoration and energy conservation. Recent research on the evolution of cooperation highlights the potential for reputational mechanisms and scorekeeping to foster cooperation in online social networks. Nested bordered tug-of-war models suggest that challenges that elicit between-group competition will increase within-group cooperation. Based on social psychology, we note that increased levels of interest and cooperation can be fostered by social norms comparisons in combination with visually compelling representations of individual and collective benchmarks. Finally, we explore how properties of social networks themselves enhance the spread of behaviors through the three degrees rule, homophily, social contagion, and the strength of weak ties. In an age where environmental toxins, habitat loss, population growth, and climate change threaten our future health and survival, we present testable hypotheses and argue for the importance of field experiments to better understand the nexus between the social self, group identity, social networking effects, and potential for supporting collective action via the social Web.

Online social networks have an enormous impact on opinions and cultural trends. Also, these platforms have been revealed as a fundamental organizing mechanism in country-wide social movements. Recent events in the Middle East and North Africa (the wave of protests in the Arab world), across Europe (in the form of anti-cuts demonstrations or riots) and in the United States have generated much discussion on how digital media is connected to the diffusion of protests. In this chapter, we investigate, from a complex network perspective, the mechanisms driving the emergence, development and stabilization of the “Indignados” movement in Spain, analyzing data from the period between April 25 and May 26, 2011. Using 70 keywords related to the movement, we analyze 581,749 Twitter messages coming from 87,569 users. The online trace of the 15M protests provides a unique opportunity to tackle central issues in the social network literature like recruitment patterns or information cascades. These findings shed light on the connection between online networks and social movements and offer an empirical test to elusive sociological questions about collective action.

While in 2011 protesters took to the streets and gathered in Tahrir Square in Cairo, people in Egypt and across the world started discussing the protests on Twitter. With its short and simple messages, Twitter turned out to be an effective venue for diffusion of ideas and opinions. This chapter explores how social movements and other forms of collective action may be able to use Twitter to frame grievances in ways that resonate with their target audience. In particular, using Twitter data collected during the protests in Egypt, this paper examines whether the use of Twitter by Egyptian activists helped to diffuse the Arab Spring frame across Egypt and generate greater social cohesion around their messages. Our results lend tentative support to the hypothesis that it in fact did. When activists or members of the traditional media are in positions of brokerage, the level of cohesion within a community is greater than it would be otherwise. That highly central activists have the largest effect suggests that because their position within the network allows them to broker the flow of information, they are able to use Twitter to frame events in ways that resonate with others.

This chapter focuses on Morocco, presenting research conducted on the Moroccan blogosphere between 2007 and 2009, before the Arab Spring, in which a burgeoning civil society space with some evidence of collective action was apparent. Despite this online activism and the highest level of Internet penetration in North Africa, the Moroccan government withstood Arab Spring protests. While the religious and political legitimacy of the Moroccan monarchy is a key factor in explaining this difference, there are also significant socioeconomic and linguistic cleavages that were mirrored in the online space. Nevertheless, the Moroccan blogosphere leading up to the events of 2011 provides a rich public narrative that includes collective action unique to this historically authoritarian North African country. The chapter will utilize selected collective action literature to examine the nature of this narrative and then examine it in light of several Arab Spring protests that did occur in Morocco, concluding that, while the monarchy retains its power and online collective action does not reach the majority of citizens, online social and political expression do represent a potentially significant development in Morocco’s public sphere.

This paper outlines the divergent tactics of two groups of American Muslim collective actors, which are conceptualized in terms of organizational and organic, in addressing the issue of hijab and discrimination in the workplace. The organizational form, represented by the Council for American-Islamic Relations (CAIR), uses highly publicized awareness campaigns to promote civil rights, while the organic form, represented by the hijabi fashion community, tends to opt out of drawing attention to the discrimination that is commonplace in their dealings with other Americans. The term organic is employed to demarcate the differences between structured grassroots and nonhierarchal collective action carried out through the Internet. A qualitative content analysis of seven hijabi fashion blogs is conducted to cull thematic continuities among these bloggers and their commentators in regard to a few well-publicized campaigns against hijab discrimination launched by CAIR and other discussions of discrimination in workplace. The paper argues that the tactics of the organic form of collective action develop discursively through discussions on these websites about how hijabis can navigate various situations, grounded in a shared sense of identity and context. These tactics are customized for experiences of hijabis “on the ground” as opposed to the organizational tactics, which model the successes of other civil rights organizations. The paper concludes by suggesting that the organizational tactics might be more effective, in the context of the continued expansion of Islamophobia in the American culture, if American foreign policy and mainstream media did not continue to promote the connection between Islam and extremism.