The use of modularity algorithms as part of the conceptualization of the perspectival form in large networks Lorena Regattieri Jean Maicon Medeiros Fabio Malini Labic - UFES Labic - UFES Labic - UFES Federal University of Espirito Santo Federal University of Espirito Santo Federal University of Espirito Santo regattie@ualberta.ca jeanmrmedeiros@gmail.com fabiomalini@gmail.com ABSTRACT the algorithm that seeks to analyze them, as the natural language vocalized on them, are in continuous process of interrelation to How can we identify perspectives in large networks through the interpret the social world. The algorithm alone does not explain application of modularity algorithms? In the digital humanities these relationships. But collective action, today generative of [1][2], there is a fair number of scholarly work exploring digital traces [4] cannot be explained alone, only with historical computational routines to cluster and analyze enormous amounts social theories of the humanities. of data. Recently, social data became a valuable source to study Graph clustering or community detection [5][6][7][8] in complex collective phenomenon, they provide the means to comprehend networks have a long history of research in machine learning and human collectivity by using graph network analysis. In this paper, graph theory [9]. The studies in the field have gain attention from we describe our approach on the manner of post-social several areas, the most common studies are find in biology, anthropology [3] and social sciences using technical methods: technological, and physics. In the meantime, the literature in quantitative analysis and modularity optimization. The Natural Language Processing [10][11] and Probabilistic Neural computational turn is part of the ongoing process to conceptualize Networks [12] have shown us the possibilities in document the "perspectival form", as the other would be the semantic modeling, text classification, and collaborative filtering for large analysis of the qualitative data. This technique uses a python corpora. script to extract the co-occurrence hashtags network from a Twitter dataset in order to apply in the context of the open-source In this paper, we describe a certain method developed by software Gephi. Our experiments successfully exhibit how social researchers at Laboratory of Studies in Images and Cyberculture networks can be unfolded when submitting a sample dataset of (LABIC)1, located at Federal University of Espirito Santo hashtags to the procedure found in the critical dimension of (UFES), Brazil. It consists in being a simple, but efficient and computational models. Therefore, it discovers the flow of peculiar method developed to support studies in social sciences perspectives when the strategy is follow in new workspaces, and humanities. Our novel perspectival framework uses a Twitter creating then categories that reveals points of view underneath the dataset publicly available online, thus, a variety of 500k+ tweet controversy. Concluding, this study presents a theoretical and twitter feeds are draw on for examples. Such method uses Gephi methodological framework based in the post-structuralists, a [13] and its algorithms, resulting in visualizations and statistics. composition that aims to support studies in different fields of The method aims to find communities on a network formed by co- social sciences and humanities. occurrence of hashtags in a tweet, in other words, we set a network of hashtags in order to compose a multiplicity. Categories and Subject Descriptors The relevance in the contemporary context of online network sites D.3.2 [Programming Languages]: Language Constructs and serves as the means to interpret the political and collective Features – abstract data types, polymorphism, control structures. actions, that is why Twitter is our "field" of work. We consider the I.5.3 [Pattern Recognition]: Clustering - algorithms, similarity social network a rich terrain of dispute, noticing the many measures. uprisings around the world: #OccupyWallStreet, #15M, J.4 [Computer Applications] Social and Behavioral Sciences – #OccupyGezy, #VemPraRua, and #NãoVaiTerCopa. Other social Sociology phenomena can be considered a perspective in progress, like #ClimateChange. While recently proposed methods practice General Terms detecting topics in historical and literature corpus by using Documentation, Human Factors, Theory, Algorithms and Design. probabilistic topic modeling [14], we aimed to present a new Keywords methodology to underline not just a topic model procedure for digital data, but to reveal the points of view in constant flow, in Post-Social Anthropology, Network Science, Amerindian fact, profiles in a battlefield. Perspective, Modularity Algorithms, Complex Networks. In order to comprehend the layers of texts in the digital traces left by humans, we rely in the actor-network-theory [15]. The main 1. INTRODUCTION idea is to work in the same level of both, the actors and its This paper understands that social networking is an anthropological phenomenon. A graph of social networking is a 1 http://www.labic.net material representation of human relationships. Therefore, both attributes. “A network is fully defined by its actors." [16] ANT hashtag, based in our tests, prove to be the better solution for and network analysis provide the argument to study digital data social scientists working with data science. When using the without worrying about the standpoint of the individual or hashtag sign, the user is segmenting a topic of interest, more than collective. It is possible to negotiate to one level to another, from that: he allies itself to a point of view on a subject. It is simple to the parts to its whole, only by continuously rearranging the actors, analyze that once someone have generated a tweet and already or the nodes. There is no overlapping, it is matter of reorganizing used a hashtag, it is as if the user is already categorizing the text ones positioning. The cartography of controversies [17] is the for the researcher. In addition, the hashtag represents the existence didactical application of the ANT, it serves as a range of of a debate that matter or even just some cause that people aimed techniques to explore public debates. Observation and description to call attention for it. Either way, the many ways that people give is essential to the scholarly work done in this paper. In this meaning to points of view by indexing value to a specific word meeting between computing methods and the post-social will qualified a perspective in the public debate. anthropology [3], the Lautorian socio-technical networks approach will support the process of revealing points of view in disputes. Our methodological framework poaches the Amerindian Perspectivism [18] to find the foundation for our ongoing experiments to compose a "perspectival form" in large networks. Again, they are called large networks because they are made of thousands or even millions of nodes and edges. Most importantly, comprehending the node as a social profile in the network, thus, the edges, as the link between One and the Others. Then, a network is only constituted by the existence of the other. Eduardo Viveiros de Castro subverts the idea we have of cannibalism, which is an idea that guided in the conception of "to cannibalize" the other is to eat the other. He inverts the enunciation, saying that cannibalism is a way out of self to go into the other, for each other. The node as a profile on the social network it increasingly comes out of the self to "retweet" what is better or worse from another, therefore, assuming the point of view of that other (and they are of many types). Nowadays, the other is the element that captures us. It is an anthropological turn, which we live in. In fact, this is our inspiration to reconceive a qualitative- quantitative method of analyses throughout machine steps, which Figure 1: The figure shows the center of the network we know in computing as the algorithm. When applying these #VemPraRua, consisting of 125 000 Retweets. Only when procedures to comprehend collective phenomena, it produces new analyzing the perspectives (networks around the center) it is perspectives and methods. The computer requires the cascade of possible to understand the different perspectives on the texts and hashtags we collected in our dataset to metamorphose network. into the grid of numbers. [19] The framework we have been testing is based in the Louvain algorithm [20], in which we 2. THE ANTHROPOLOGICAL THOUGHT compute to maximize the network modularity. AND NETSCIENCE The use of Twitter, in particular, has led us to a couple of challenges in text clusterization process. As the qualitative The substance of our framework is in how we interpret modules research process evolve and the number of tweets increases to without changing the levels or scale of plan. In online social millions, categorization and the topology of the network became a networks, we argue the existence of movements and circulation in problem. “The whole is always smaller than its parts”.[16] A large a flat surface with no consideration to hierarchy. The node is network features an illusory representation. It overlaps itself in situated in the terrain of dispute, one that is only defined by its distinct layers, social groups and thoughts, as if was part of a network.[16] In this case, when exploring the dots in the graph, single network topology. In theory, the social is crossed by a which in our dataset are the hashtags, the actor moves to the multiplicity of natures, perspectives, worldviews, produced by network, interacting with others in the same level. This is where different human groups. And here is our hypothesis: thereby, we stand with Latour, in a flat ontology. every network is, rather, a network of perspectives, which are usually in dispute. The approach we reclaim to study online networks is the one inherit from Pierre Clastres.[3] In any case, we propose a The methodology that first was based in data mining and descriptive study of a terrain which we understand to be in clustering thousands of words needed a new framework. Given constant dispute. This allows us to rely once again in the this problem, we created the hashtag network script. After the indigenous world, which there is a surviving violence itself, a consultation of literature available [21] new possibilities have reference to problematize the thesis of repulsion and attraction of rise, from the initial goal to find a method to fastening the algorithm of modularity. In short, we make use of the concept clusterization of words and categories to the use of hashtags to of cannibalism, which derives from the complex notion of find perspectival forms. Nowadays, the discussions indexed to a cannibalism. Applied in the field of hashtags as views, this very hashtag often become themes of conversations between halls. The cannibalism lives of the perspectival forms within the network revealing then a mode of operationalization. This is a process of studied in information networks, a political aspect that we find in maximal reduction of one single node and another, almost like a the modes of existence peculiar to the indigenous society, a way microscopic work to see the minor points of view. "Exchange, or, of existence, i.e., a substantially minor of existence, in a minority the circulation of perspectives: exchange of exchange, that is, character. Therefore, we are concern with the mechanisms that change.” [22] inhibit or block the emergence of a totalizing discourse. Therefore, "perspectivism does not state the existence of a In data science, complex networks [23] are identified as very large multiplicity of points of view, but the existence of the point of networks, millions or billions of nodes and edges. This sort of view as a multiplicity." [27] networks occur in different contexts, it is possible to recognize in nature, society, technology, economics, etc. One of its Modularity is one of the possible measure for detecting fundamental characteristics is the temporal evolution aspect. communities in complex networks. A set of nodes categorize itself Complex systems constitute themselves of many non-identical as community by its modularity if the fraction of links between elements connected by a diversity of interactions. Several them is higher that expected ia network called “null model”, networks in nature, ecology, economics, human relationships in which is used as a reference. [28]. A complex network with a high social networks and the web has the same topological structure. modularity indicates strong community structure, in other words, They are known scale-free networks [24]. We will associate this the nodes inside the same community has a dense connectedness computational concept with the understanding of networks from and has a sparse connexion between other communities. Bruno Latour. The algorithm applied in this paper to find communities, since we In this sense, the actor-network theory (ANT) comes in hand with use Gephi [13], is the Louvain Method. Such method does the inquiry we propose. The large networks in this empirical study community detection in weighted graphs and has characteristics come from the NET, which we purposely stress in the same way such as greedy heuristic, local optimization of modularity, very Latour does with ANT. To trace the circulation and interactions of fast (complexity O(nlog(n), n: number of nodes), non- points of view and objects, ANT is going to explore the deterministic, return hierarchical partition. The Louvain Method constitutive connections between actors (the actants), both is an “algorithm that finds high modularity partitions of large animate and inanimate, and the generative potential of those networks in short time and that unfolds a complete hierarchical interactions. In his own words, “(…) network does not designate a community structure for the network, thereby giving access to thing out there that would have roughly the shape of different resolutions of community detection.” [20]. Think of the interconnected points, much like a telephone, a freeway, or a network as a perspective. Well then, the nodes that compose such sewage ‘network’… It qualifies its objectivity, that is, the ability network will form an alliance, ie, they will form a covenant of each actor to make other actors engage in unexpected relationship between viewpoints. The link between two nodes is relations.”[15] More precisely, we consider social profiles as exactly the distance between them, and also, the distance between living things. Often happens that in the information networks, it is points of view. It turns out, then, that the way which we apply the not possible to recognize the "form", only the information. By that algorithm maximizing the modularity, the network is partitioned we meant the profiles that uses the language like a human into modules, testing all nodes until no node can belong to component, but notice, they are only information, or robots to act another module. It is a dimension of alterity, the same as found in as man. However, the meaning arises from the disparate actions. Amerindian perspectivism. "Perspectives encourage you to [27] believe OUT of them." (Roy Wagner)[2] The algorithm repeats this process of exchange and change, successive times for all We mend our theoretical foundations in the connections we nodes. Autophagy is a survival of hashtags in the network. A perceive between anthropology and post-structuralism. Which roundup of alliances. summing up is circumscribed in the post-social-anthropological net of authors listed here, considering then the deleuzian concept that comes from the mathematics, where we find the means to 4. METHODOLOGY comprehend the multiplicity as a point of view. It creates a new kind of entity, rejecting any generalizations, the one we know as "The object as such: why a perspective is not a ‘rhizome’. Therefore, a rhizomatic multiplicity does not, in fact, representation"[31]. behave as one, because it is not possible to do that when it operates as assemblages of becomings. Here is when Latour meets The first step of the method is, of course, to have the dataset to be Deleuze and the notion of actor-network, one which the network analyzed, the collection of tweets formated in a comma separated cannot be one thing, yet, again, because anything can be file (csv). The tool utilized to get these tweets is called considered a network.[22] And finally, in the next section, yourTwapperKeeper2. The procedure begins with the choice of a building up from this interdisciplinary dialogue, we present how term or hashtag, the tool does the job of archiving the massive the amerindian perspectivism support our hypothesis in exploring amounts data. This process provides a historiography of what the complex world of large networks, finding a perspectival form have been vocalized related to the research expression. With within the modularity algorithm. enough data to go through ethnographic rendering, we can go to the “field”, which for us means to explore a database of entities 3. THE PERSPECTIVAL FORM WITHIN and attributes. THE MODULARITY The second step is data processing. As we know, hashtags are one of the most commonly used form of categorization and indexation We were called into the indigenous world to reflect the network among users in social networks, such as Twitter and Facebook. studies, mainly due to a natural notion of multiplicity in the indigenous society.[26] Primarily because we have for long 2 http://www.github.com/540co/yourtwapperkeeper One can say that the hashtag summarize the content of the tweet, The dataset consists in 271.013 tweets that were collected positively or negatively, confirming it or contradicting it. So, this between february 4th and may 4th, 2014. This image is a view next step consists in creating a “Hashtag network” from the tweets between acts in the third step of our method, after the first pass of previously collected. The Hashtag network is a complex network the modularity optimization algorithm and rearrangement of the that links hashtags if there is co-occurrence between them in the nodes with highest weighted degrees in each perspective. It is an same tweet and it forms a weighted network, as it can happen overview of #worldcup’s hashtags network as the main twice with the same hashtags. The creation of this complex perspectives are emphasized. As we can see a certain noise or network is provided by a script programmed in our lab and its distortion is identified in the network, as in “#cricket”, where the output is a csv file that will be used in the data mining process. hashtags mean to mention the cricket world cup, or in #teamfollowback, where users tend to flood their timeline in order The third step relies on drawing the network and manipulating to get more followers. with its structure. In order to visualize the network, we import it to Gephi. For now, the first view of the network is a hairball, a In this perspective of the network (Figure 2), it is visible the completely unintelligible graph. This is the time when modularity english topic being discussed. The different subtopics, evident comes into the picture. But before that, there’s a very important among the nodes, make this assumption clear. And so, as seen in act. We will have to delete the “main node”, in other words, the the hashtags #epl, #bpl and #premierleague, meaning the hashtag that links all nodes. Therefore, the next move is to apply discussion of the English Premier League a.k.a. the english “Modularity”, set the parameters of your choice and wait until national championship, and in #nufc and #lfc, meaning calculation is over. Next step, applying the modularity class Newcastle, United FC and Liverpool FC, both english teams, and calculated for each node and thus forming the communities. One last, but obviously not least, the hashtag #rio, that clearly connects way to apply it on the network is setting the colours to the nodes, the main discussion #worldcup, as the English team is going to thereby emphasizing the communities, in our case, the topics of train in the Rio De Janeiro city before the cup. discussion. The next important move is to calculate the “Average Weighted Degree” which gives the user a way to apply different sizes to the nodes from their weighted degree, and this was the next step. The network isn’t longer a hairball and the recognition of communities is clearer, thus, as for the biggest nodes in each community, they define the points of view of that community. Lastly, each community is a network of point of views and they are distributed through Gephi’s workspaces. Now, we apply the modularity and calculate the average weighted degree again. The final touch consists in setting the design of the graph with the “Circular Layout” option, it is also more visually interesting to order the nodes based in the modularity class. We advise for matter of design to find the node with higher degree, in which we will identify the most prominent point of view of the particular network. By now, we expect for terms of visualization and exploration to have a network of hashtags, i.e, the perspectival form of the network. Figure 3: #qatar perspectives on #worldcup. After emphasizing the nodes with highest weighted degrees, the 4.1 The case with the #WorldCup human interaction, as research, is truly required to engage the process of perspective perception. The hashtag #ukraine involves the perspective of protests and their recent history with russia, the multiples hashtags are seen in the composition of point of views. We can identified the following words: #crimea, #sanctions, #russiainvadesukraine, and #worldwar3. But also in this perspective, there is fractal element, because we can also foresee the hashtags #wc2018, #2018worldcup, and #worldcup2018, which suggests that people are already expressing concerns on the country that will host the next world cup, in 2018. As for #gymnastics, the perspective lies in the gymnastics world cup that happened in doha in 2014, which can be seen as noise in our main investigation. And in #qatar, where the 2022’s world cup will be hosted, the multiplicity, as point of view, is focusing on several discussions involving #humanrights, #workersrights, #slavery, and such. 4.2 The case with the #ClimateChange Figure 2: #worldcup’s main perspectives and #england perspectives on #worldcup. The dataset on climate change was collected between February, 2nd and May, 5th of 2014. In total, we have exactly 1.048.576 million tweets. To analyze the data, we put together a hashtag network of 21.415 nodes. The number for the hashtags provides a sample of the "heat" of the debate online. In the Figure 4, we had only computed the modularity the first time, the graph display the partition of the network into modules. The points of view with higher average weighted degree indicates as results: #carbonbubble, #energy, #obama, #tcot, #nsa, #gree#, #news, #ows, #truth, #obama, #bbcnews, #fracking, #travel, #jobs, #earthday, #organic, #climate and #climate2014. Who is what in this network? Appearances can be deceptive, although, a few interesting revelations appears already. For instance, #tcot means Top Conservatives on Twitter, this network has a longer effect in the network because it has has an alliance to american Tea Party. Figure 5: The blue network arises as a perspectival form with high modularity. 5. CONCLUSION In this paper we have presented theoretical references in Post- Social Anthropology and Complex Networks to support our methodological framework for studies of social information data. Twitter is a rich field of productions, it can create alarming discussions over the necessity to debate the ecological crises, such as the hashtag #climatechange. There is a social memory within the hashtag, that’s why in this research we addressed the exploration of points of view though the hashtags in the network. However, the hashtag is also a fictional character that brings together a collective memory and puts it to act in the public space, influencing the understanding of what we understand to be reality. This is not a simulacro 2.0, it is a practice that activates a mode of human existence, the fictional, to expand our critical capacity. In the case of #climatechange, we confirmed the existence of a Figure 4: #climatechange perspectives. variety of networks in the large network. Different perspectives that are completely distinguishable. Such as, the distance between #actonclimate and #teaparty.The analysis of the #worldcup Still, note that we have design the perspectival forms in order to assemble the perspectival form as a multiplicity. Inviting us to dig visually demonstrate the capacity of some point of views to into the point of view, emphasizing that it is not possible to establish more regimes of alliances. In this orange network of generalize the network. This procedure, that analyzes the co- point of views, the high value of internal modularity, clearly occurrence of hashtags in a dataset of tweets, leaves behind tweets echoing the american Republican Party tongue. At the same time, with no hashtags and one hashtag only. This implicates on a the green network maintain a link to the orange network, the certain limitation for the method, but also it focuses on its main multiple points of view embedded in this green network are goal: to study the connection between the hashtags of a tweet and #globalwarming and #deniers. No wonder, this perspectival form perceive the perspectival form originated by its connections on a preserve this alliance with American conservative party. complex network. The blue network proposes a perspectival form of the We describe the intercorrelation of algorithms and the humanities, anthropocene. A hahstag itself, #anthropocene reflects the together it composing a powerful tool that allows a routine of data currently reality of concerns brought by the notion of Gaia. mining, processing, and visualization of social information. Bringing issues like # energy, # food, # weather, a dimension of Applying our research methodology has evidenced our hypothesis the ecological crisis. The reflection of man before the outburst of since it indicates that there are variety of points of view, so a more Gaia. In this case, the blue network has links to the different detailed study of network demands to take into account the perspectival forms, such as the #cdnpoli, a network of the point of perspectives of the network. It is also important to note, views involving the environmental crises in Canada. In there, we perspectives converge in the same direction, so the groups are can find the #KXL #KeystoneXL, the hashtags used about the oil well defined in which side it defends. Our method indicates that debate. research involving informational networks, such as studies concerning degree, sentiment, hub and authority, which do not take into account the perspectives in dispute in the networks, will tend always to reach conclusions that privilege the richest nodes with more connections. For future work, we plan to refine our methodological frame with tests in other datasets and to improve [14] Mimno, D, and McCallum, A. 2007. Mining a digital library the visualization of the perspectival form of the network. for influential authors. Joint Conference on Digital Libraries (JCDL) 2007, Vancouver, BC, Canada. 6. ACKNOWLEDGMENTS [15] Latour, B. 2007. Reassembling the Social: An Introduction to Actor-Network-Theory. Oxford: Oxford University Press. Funding for the project generously supplied by National Council [16] Latour, B, Jensen, P, Venturini, T, Grauwin, S, and Boullier, for Scientific and Technological Development (CNPq), National D. 2012. The Whole is always smaller than its parts. In Academic Cooperation Program (Procad), Coordination of British Journal of Sociology. Improvement of Higher Education Personnel (Capes), Foundation [17] Venturini, T. 2010. Building on faults: how to represent of the Ministry of Education (MEC). Our thanks to the team at the controversies with digital methods. SAGE Journals. Laboratory of Studies in Image and Cyberculture (LABIC) for the December 5, 2010. ongoing support. [18] VIVEIROS DE CASTRO, E. 2002. A Inconstância da Alma Selvagem e Outros Ensaios de Antropologia. São Paulo: 7. REFERENCES Cosac & Naify. 552 pp. [19] Berry, D. 2011. The Computational Turn: Thinking About [1] Moretti, F. 2013. Distant Reading. London: Verso. 254 pp. the Digital Humanities. In The Digital Humanities: Beyond [2] Jockers, M. 2013. Macroanalysis: Digital Methods and Computing. v 12. Literary History. University of Illinois Press. 208 pp. [20] Blondel, V.; Guillaume, J.; Lambiotte, R.; Lefebvre, E. [3] Viveiros de Castro, E, Goldman, M. 2012. Introduction to 2008. Fast unfolding of communities in large networks. In Post-Social Anthropology. In HAU: Journal of Ethnographic Journal of Statistical Mechanics: Theory and Experiment Theory 2 (1): 421-433. 2008 (10), P10008 (12pp) doi: 10.1088/1742- 5468/2008/10/P10008. ArXiv: [4] Latour, B. 2007. Beware your imagination leaves digital http://arxiv.org/abs/0803.0476 traces. In Times Higher Literary Supplement, 6th April 2007. [21] Grauwin, S. 2011. Exploring Social Phenomena with [5] Lee, C, and Cunningham, P. 2013. Community detection: Complex Systems Tools: The Journey of a Physicist in an effective on large social networks. In Journal of Complex Interdisciplinary Playground. ENS Lyon, thesis. Networks (2014) 2, 19-37. [22] Viveiros de Castro, E. 2010. Intensive Filiation and Demonic [6] Elhadi, H, and Agam, G. 2013. Structure and Attributes Alliance. In Deleuzian Intersections: Science, Technology, Community Detection: Comparative Analysis of Composite, Anthropology. Oxford: Berghahn. Ensemble and Selection Methods. In SNA KDD 2013 International Workshop on Social Network Mining and [23] Gomes, L.; Almeida, V.; Almeida M. J.; Castro, F.; Analysis held in conjunction with ACM SIGKDD Conference Bettencourt; L. 2009. Quantifying Social and Opportunistic on Knowledge Discovery and Data Mining, August 2013. Behavior in Email Networks. Advances in Complex Systems 12(1): 99-112. [7] De Meo, P, Ferrara, E, Fiumara, G, and Provetti, A. 2011 Generalized louvain method for community detection in [24] Barabási, A.-L.; Albert, R. 1999. Emergence of scaling in large networks. In Intelligent Systems Design and random networks. Science 286, 509–512 Applications (ISDA) 88-93 [25] Simondon, G. 2010. On the mode of existence of technical [8] Fortunato, S, and Barthélemy, M. 2006. Resolution limit in objects: Third part. (N. Mellamphy, D. Mellamphy, & N. B. community detection. In Proceedings of the National Mellamphy, Trans.). London. Retrieved November 15, 2012, Academy of Sciences of the United States of America. v 104, from 1, 36-41. http://www.academia.edu/539031/Gilbert_Simondon_The_E ssence_of_ Technicity [9] Milkov, E, Cohen, W, and Ng, A. 2006. Contextual Search and Name Disambiguation in Email using Graphs. In SIGIR. [26] Viveiros de Castro, E. 2013. La Mirada Del Jaguar: Introducion al Perspectivismo Amerindio. Tinta Limon. [10] Chang, J, Boyd-Graber, J, and Blei, D. 2009. Connections Buenos Aires. between the Lines: Augmenting Social Networks with Text. In Refereed Conference on Knowledge Discovery and Data [27] Viveiros de Castro, E. 2012. “Immanence and Fear: Stranger Mining, 2009 events and subjects in Amazonia”. In HAU: Journal of Ethnographic Theory. Vol 2 (1): 27-43. [11] Blei, D. 2014. Build, compute, critique, repeat: Data analysis with latent variable models. Annual Review of Statistics and [28] Vincenzo, N. 2008. Modularity for community detection: Its Application 1:203-232, 2014. history,perspectives and open issues. Found at: http://supernet.isenberg.umass.edu/fulbright- [12] Ciarelli, P, Oliveira, E, and Salles, E. Multi-label incremental catania/workshop-talks/nicosia-nagurney-daniele- learning applied to web page categorization. Neural workshop.pdf. Last access: 06/06/2014. Computing and Applications 24(6): 1403-1419 (2014) [29] Wagner, R. 2012. Facts force you to believe in them; [13] Bastian M., Heymann S., Jacomy M. 2009. Gephi: an open perspectives encourage you to believe out of them. An source software for exploring and manipulating networks. introduction to Viveiros de Castro’s magisterial essay. In International AAAI Conference on Weblogs and Social HAU: Journal of Ethnographic Theory. Vol (1): 11-4. Media. 2009.