Abstract

We test the existence of anticipated shocks in online activity, a class of collective dynamics that does not fit in the state of the art theory on social response functions. We use data on shares and views to Youtube videos, measuring their time series to classify them according to their dynamical class. We find evidence of the existence of anticipated shocks, and that they are more likely to appear in word-of-mouth interaction than in attention dynamics. Our results show that not all exogenous events in online activity are unexpected, calling for new models that differentiate social interaction and attention dynamics.

Abstract

Through the analysis of collective upvotes and downvotes in multiple social media, we discover the bimodal regime of collective evaluations. When online content surpasses the local social context by reaching a threshold of collective attention, negativity grows faster with positivity, which serves as a trace of the burst of a filter bubble. To attain a global audience, we show that emotions expressed in online content has a significant effect and also play a key role in creating polarized opinions.

Remarks

Accepted as a poster.

Abstract

We study the changes in emotional states induced by reading and participating in online discussions, empirically testing a computational model of online emotional interaction. Using principles of dynamical systems, we quantify changes in valence and arousal through subjective reports, as recorded in three independent studies including 207 participants (110 female). In the context of online discussions, the dynamics of valence and arousal are composed of two forces: an internal relaxation towards baseline values independent of the emotional charge of the discussion, and a driving force of emotional states that depends on the content of the discussion. The dynamics of valence show the existence of positive and negative tendencies, while arousal increases when reading emotional content regardless of its polarity. The tendency of participants to take part in the discussion increases with positive arousal. When participating in an online discussion, the content of participants' expression depends on their valence, and their arousal significantly decreases afterwards as a regulation mechanism. We illustrate how these results allow the design of agent-based models to reproduce and analyze emotions in online communities. Our work empirically validates the microdynamics of a model of online collective emotions, bridging online data analysis with research in the laboratory.

Abstract

The QWERTY effect postulates that the keyboard layout influences word meanings by linking positivity to the use of the right hand and negativity to the use of the left hand. For example, previous research has established that words with more right hand letters are rated more positively than words with more left hand letters by human subjects in small scale experiments. In this paper, we perform large scale investigations of the QWERTY effect on the web. Using data from eleven web platforms related to products, movies, books, and videos, we conduct observational tests whether a hand-meaning relationship can be found in text interpretations by web users. Furthermore, we investigate whether writing text on the web exhibits the QWERTY effect as well, by analyzing the relationship between the text of online reviews and their star ratings in four additional datasets. Overall, we find robust evidence for the QWERTY effect both at the point of text interpretation (decoding) and at the point of text creation (encoding). We also find under which conditions the effect might not hold. Our findings have implications for any algorithmic method aiming to evaluate the meaning of words on the web, including for example semantic or sentiment analysis, and show the existence of "dactilar onomatopoeias" that shape the dynamics of word-meaning associations. To the best of our knowledge, this is the first work to reveal the extent to which the QWERTY effect exists in large scale human-computer interaction on the web.

Abstract

Dodds et al. (1) present a universal positivity bias—in 10 human languages—that they claim is independent of word frequency. This result contradicts previous findings (2, 3) in which a relationship between word happiness and frequency is reported for a variety of languages and large-scale datasets. To better understand this contradiction, we reanalyze the labMT (language assessment by Mechanical Turk) data produced in Dodds et al. (1) against a larger reference lexicon (3). Our reanalysis shows that the data used in Dodds et al. (1) does not support their claims.

Abstract

The availability of data on digital traces is growing to unprecedented sizes, but inferring actionable knowledge from large-scale data is far from being trivial. This is especially important for computational finance, where digital traces of human behaviour offer a great potential to drive trading strategies. We contribute to this by providing a consistent approach that integrates various datasources in the design of algorithmic traders. This allows us to derive insights into the principles behind the profitability of our trading strategies. We illustrate our approach through the analysis of Bitcoin, a cryptocurrency known for its large price fluctuations. In our analysis, we include economic signals of volume and price of exchange for USD, adoption of the Bitcoin technology and transaction volume of Bitcoin. We add social signals related to information search, word of mouth volume, emotional valence and opinion polarization as expressed in tweets related to Bitcoin for more than 3 years. Our analysis reveals that increases in opinion polarization and exchange volume precede rising Bitcoin prices, and that emotional valence precedes opinion polarization and rising exchange volumes. We apply these insights to design algorithmic trading strategies for Bitcoin, reaching very high profits in less than a year. We verify this high profitability with robust statistical methods that take into account risk and trading costs, confirming the long-standing hypothesis that trading-based social media sentiment has the potential to yield positive returns on investment.

Remarks

Online visualization at www.sg.ethz.ch/btc

Abstract

Recent grassroots movements have suggested that online social networks might play a key role in their organization, as adherents have a fast, many-to-many, communication channel to help coordinate their mobilization. The structure and dynamics of the networks constructed from the digital traces of protesters have been analyzed to some extent recently. However, less effort has been devoted to the analysis of the semantic content of messages exchanged during the protest. Using the data obtained from a microblogging service during the brewing and active phases of the 15M movement in Spain, we perform the first large scale test of theories on collective emotions and social interaction in collective actions. Our findings show that activity and information cascades in the movement are larger in the presence of negative collective emotions and when users express themselves in terms related to social content. At the level of individual participants, our results show that their social integration in the movement, as measured through social network metrics, increases with their level of engagement and of expression of negativity. Our findings show that non-rational factors play a role in the formation and activity of social movements through online media, having important consequences for viral spreading.

Abstract

Political polarization is traditionally analyzed through the ideological stances of groups and parties, but it also has a behavioral component that manifests in the interactions between individuals. We present an empirical analysis of the digital traces of politicians in politnetz.ch, a Swiss online platform focused on political activity, in which politicians interact by creating support links, comments, and likes. We analyze network polarization as the level of intra-party cohesion with respect to inter-party connectivity, finding that supports show a very strongly polarized structure with respect to party alignment. The analysis of this multiplex network shows that each layer of interaction contains relevant information, where comment groups follow topics related to Swiss politics. Our analysis reveals that polarization in the layer of likes evolves in time, increasing close to the federal elections of 2011. Furthermore, we analyze the internal social network of each party through metrics related to hierarchical structures, information efficiency, and social resilience. Our results suggest that the online social structure of a party is related to its ideology, and reveal that the degree of connectivity across two parties increases when they are close in the ideological space of a multi-party system.

Abstract

What is the role of social interactions in the creation of price bubbles? Answering this question requires obtaining collective behavioural traces generated by the activity of a large number of actors. Digital currencies offer a unique possibility to measure socio-economic signals from such digital traces. Here, we focus on Bitcoin, the most popular cryptocurrency. Bitcoin has experienced periods of rapid increase in exchange rates (price) followed by sharp decline; we hypothesize that these fluctuations are largely driven by the interplay between different social phenomena. We thus quantify four socio-economic signals about Bitcoin from large datasets: price on online exchanges, volume of word-of-mouth communication in online social media, volume of information search and user base growth. By using vector autoregression, we identify two positive feedback loops that lead to price bubbles in the absence of exogenous stimuli: one driven by word of mouth, and the other by new Bitcoin adopters. We also observe that spikes in information search, presumably linked to external events, precede drastic price declines. Understanding the interplay between the socio-economic signals we measured can lead to applications beyond cryptocurrencies to other phenomena that leave digital footprints, such as online social network usage.

Abstract

The subjective nature of gender inequality motivates the analysis and comparison of data from real and fictional human interaction. We present a computational extension of the Bechdel test: A popular tool to assess if a movie contains a male gender bias, by looking for two female characters who discuss about something besides a man. We provide the tools to quantify Bechdel scores for both genders, and we measure them in movie scripts and large datasets of dialogues between users of MySpace and Twitter. Comparing movies and users of social media, we find that movies and Twitter conversations have a consistent male bias, which does not appear when analyzing MySpace. Furthermore, the narrative of Twitter is closer to the movies that do not pass the Bechdel test than to those that pass it. We link the properties of movies and the users that share trailers of those movies. Our analysis reveals some particularities of movies that pass the Bechdel test: Their trailers are less popular, female users are more likely to share them than male users, and users that share them tend to interact less with male users. Based on our datasets, we define gender independence measurements to analyze the gender biases of a society, as manifested through digital traces of online behavior. Using the profile information of Twitter users, we find larger gender independence for urban users in comparison to rural ones. Additionally, the asymmetry between genders is larger for parents and lower for students. Gender asymmetry varies across US states, increasing with higher average income and latitude. This points to the relation between gender inequality and social, economical, and cultural factors of a society, and how gender roles exist in both fictional narratives and public online dialogues.

Abstract

We combine user-centric Twitter data with video-centric YouTube data to analyze who watches and shares what on YouTube. Combination of two data sets, with 87k Twitter users, 5.6mln YouTube videos and 15mln video sharing events, allows rich analysis going beyond what could be obtained with either of the two data sets individually. For Twitter, we generate user features relating to activity, interests and demographics. For YouTube, we obtain video features for topic, popularity and polarization. These two feature sets are combined through sharing events for YouTube URLs on Twitter. This combination is done both in a user-, a video-and a sharing-event-centric manner. For the user-centric analysis, we show how Twitter user features correlate both with YouTube features and with sharing-related features. As two examples, we show urban users are quicker to share than rural users and for some notions of "influence" influential users on Twitter share videos with a higher number of views. For the video-centric analysis, we find a superlinear relation between initial Twitter shares and the final amounts of views, showing the correlated behavior of Twitter. On user impact, we find the total amount of followers of users that shared the video in the first week does not affect its final popularity. However, aggregated user retweet rates serve as a better predictor for YouTube video popularity. For the sharing-centric analysis, we reveal existence of correlated behavior concerning the time between video creation and sharing within certain timescales, showing the time onset for a coherent response, and the time limit after which collective responses are extremely unlikely. We show that response times depend on video category, revealing that Twitter sharing of a video is highly dependent on its content. To the best of our knowledge this is the first large-scale study combining YouTube and Twitter data.

Abstract

Measuring culture and its dynamics through surveys has important limitations, but the emerging eld of computational social science allows us to overcome them by analyzing large-scale datasets. In this article, we study cultural dynamics through the votes in the Eurovision song contest, which are decided by a crowd-based scheme in which viewers vote through mobile phone messages. Taking into account asymmetries and imperfect perception of culture, we measure cultural relations among European countries in terms of cultural anity. We propose the Friend-or-Foe coecient, a metric to measure voting biases among participants of a Eurovision contest. To validate how this metric represent cultural anity, we designed a model of a random, biased Eurovision contest. Simulations of this model show how our metrics can detect negative anities and serve as an estimator for positive anities. We apply this estimator to the historical set of Eurovision contests from 1975 to 2012, nding patterns of asymmetry and clustering in the resulting networks. Furthermore, we dene a measure of vote polarization that, when applied to empirical data, shows a sharp increase within countries of the EU during 2010 and 2011. As a result, we measure how the recent political decisions of EU states inuence the way their citizens relate to the culture of other EU members, leading to stronger cultural biases in the way they vote in the Eurovision song contest.

Abstract

We present a study political discourse and emotional expression through a dataset of Spanish tweets. We analyze the political position of four major parties through their Twitter activity, revealing that Twitter political discourse depends on subjective perception, and resembles the political space of Spain. We propose a simplified lexicon-based method to identify the topics of a tweet, which works especially well to detect the political content of tweets. Furthermore, we adapted SentiStrength to Spanish, by translating and converting an established lexicon of word valence. Under certain design decisions, this tool performs better than random, with ample room for improvement. Finally, we combined three datasets to analyze the sentiment expressed in the political tweets of four major Spanish parties, finding differences related to the status quo, and the Spanish political climate.

Abstract

We present our approach to online popularity and its applications to political science, aiming at the creation of agentbased models that reproduce patterns of popularity in participatory media. We illustrate our approach analyzing a dataset from Youtube, composed of the view statistics and comments for the videos of the U.S. presidential campaigns of 2008 and 2012. Using sentiment analysis, we quantify the collective emotions expressed by the viewers, finding that democrat campaigns elicited more positive collective emotions than republican campaigns. Techniques from computational social science allow us to measure virality of the videos of each campaign, to find that democrat videos are shared faster but republican ones are remembered longer inside the community. Last we present our work in progress in voting advice applications, and our results analyzing the data from choose4greece.com. We show how we assess the policy differences between parties and their voters, and how voting advice applications can be extended to test our agentbased models.