Lara Mondini Martins, Cássio De Alcantara, M. Barioni, Luiz Carlos De Oliveira Júnior, E. Faria
Currently, with the growth of the use of social networks, the possibilities of studies on social relationships and interactions have grown significantly. Understanding how users express their feelings and manifest their temperaments in social networks can be a step towards anticipating psychological disorders. Instagram has billions of users and is among the most used social networks today. However, it is still little explored as a source of study for human temperament. This work aims to analyze the relationships between users’ temperament and their data collected from the social network Instagram. For the analysis of textual data, two sentiment classification strategies are proposed. The sentiment classification results were satisfactory, with accuracy above 80% in three different databases. In order to analyze the relationship between the temperaments and social network data, statistical tests are used. Each user is represented by their positive and negative captions, the use of emojis in their posts, and the number of likes in their posts. Users of the same temperament are contrasted with users of other temperaments. The results indicate that depressed users post more captions with positive sentiment than hyperthymic, angry and worried users. Anxious users have more likes than depressed, hyperthymic, angry and worried users, and finally, anxious users use more emojis in Instagram captions than depressed and angry users.
{"title":"A method for analysis of human temperament in contrast to social network data","authors":"Lara Mondini Martins, Cássio De Alcantara, M. Barioni, Luiz Carlos De Oliveira Júnior, E. Faria","doi":"10.1145/3539637.3556994","DOIUrl":"https://doi.org/10.1145/3539637.3556994","url":null,"abstract":"Currently, with the growth of the use of social networks, the possibilities of studies on social relationships and interactions have grown significantly. Understanding how users express their feelings and manifest their temperaments in social networks can be a step towards anticipating psychological disorders. Instagram has billions of users and is among the most used social networks today. However, it is still little explored as a source of study for human temperament. This work aims to analyze the relationships between users’ temperament and their data collected from the social network Instagram. For the analysis of textual data, two sentiment classification strategies are proposed. The sentiment classification results were satisfactory, with accuracy above 80% in three different databases. In order to analyze the relationship between the temperaments and social network data, statistical tests are used. Each user is represented by their positive and negative captions, the use of emojis in their posts, and the number of likes in their posts. Users of the same temperament are contrasted with users of other temperaments. The results indicate that depressed users post more captions with positive sentiment than hyperthymic, angry and worried users. Anxious users have more likes than depressed, hyperthymic, angry and worried users, and finally, anxious users use more emojis in Instagram captions than depressed and angry users.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123777878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid development of optical sensors technology has accompanied a growing demand for visual measurement systems in emerging areas that need to interpret the real three-dimensional physical world, such as self-driving cars, mobile robotics, Advanced Driver Assistance Systems (ADAS), and medical diagnostic in 3D imaging. In these systems, for modeling the physical world, it is necessary to unify visual information with depth measurements. Light Field cameras have the potential to be used in such systems as a versatile hypersensor. Since Light Fields represent the scene’s visual information from multiple viewpoints, it is possible to calculate the depth information through trigonometric operations. This paper proposes a learning-based framework that allows unifying scene depth with visual information obtained from Light Fields. The structure of the proposed framework is composed of four main modules. The deep learning modules consist of (i) a depth map estimation using a siamese convolutional neural network and (ii) an instance segmentation employing region-based convolutional neural network. The others two modules apply linear transformations: (iii) a module which applies the matrix transformations with camera intrinsic parameters to generated a new depth map of absolute distances and (iv) a module to return the distance of the selected objects. For the depth map estimation module this framework proposal a siamese neural network called EPINET-FAST, which allows for generating depth maps in less than half the time of the original EPINET. A case study is presented using Dense Light Fields captured by a Lytro Illum camera (plenotic 1.0). The case study seeks to exemplify the processing time of each module, allowing researchers to isolate critical points and propose changes in the future, seeking a processing that can be applied in real time.
{"title":"A Learning-Based Framework for Depth Perception using Dense Light Fields","authors":"A. P. Ferrugem, B. Zatt, L. Agostini","doi":"10.1145/3539637.3557062","DOIUrl":"https://doi.org/10.1145/3539637.3557062","url":null,"abstract":"The rapid development of optical sensors technology has accompanied a growing demand for visual measurement systems in emerging areas that need to interpret the real three-dimensional physical world, such as self-driving cars, mobile robotics, Advanced Driver Assistance Systems (ADAS), and medical diagnostic in 3D imaging. In these systems, for modeling the physical world, it is necessary to unify visual information with depth measurements. Light Field cameras have the potential to be used in such systems as a versatile hypersensor. Since Light Fields represent the scene’s visual information from multiple viewpoints, it is possible to calculate the depth information through trigonometric operations. This paper proposes a learning-based framework that allows unifying scene depth with visual information obtained from Light Fields. The structure of the proposed framework is composed of four main modules. The deep learning modules consist of (i) a depth map estimation using a siamese convolutional neural network and (ii) an instance segmentation employing region-based convolutional neural network. The others two modules apply linear transformations: (iii) a module which applies the matrix transformations with camera intrinsic parameters to generated a new depth map of absolute distances and (iv) a module to return the distance of the selected objects. For the depth map estimation module this framework proposal a siamese neural network called EPINET-FAST, which allows for generating depth maps in less than half the time of the original EPINET. A case study is presented using Dense Light Fields captured by a Lytro Illum camera (plenotic 1.0). The case study seeks to exemplify the processing time of each module, allowing researchers to isolate critical points and propose changes in the future, seeking a processing that can be applied in real time.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127200141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brenno Lemos Melquiades Santos, E. Albergaria, D. Dias, A. B. Pigozzo, Leonardo Rocha
Mimesis is a term created by Aristotle and Plato in which art imitates life. Mimesis has been studied since ancient Greece and governed the theatrical and sculptural creations of the time. In this context, our work aims to study the effect of mimesis in the current cinematographic scenario, correlating historical events of the 20th and 21st centuries to the great cinematographic productions that follow. The question that guides our work is “Is there an increase in the release of films with a certain theme after a historical event?”. To answer this, we propose a methodology that uses two distinct data sources: one related to descriptions of historical facts from the 20th and 21st centuries extracted from Wikipedia and another with descriptions of films extracted from TMDb. Using topic modeling strategies, we automatically find the main themes related to historical events, and later, we evaluate how the description of a film is associated with the themes found. Temporal analysis is done to assess the popularity of each of the themes over time. In the results obtained by our methodology, there was a significant increase in the popularity of films that addressed themes related to historical events that occurred in an immediately preceding moment in time, corroborating the concept of mimesis.
{"title":"Correlating Historical Events and Cinematic Releases Using Web Information","authors":"Brenno Lemos Melquiades Santos, E. Albergaria, D. Dias, A. B. Pigozzo, Leonardo Rocha","doi":"10.1145/3539637.3557059","DOIUrl":"https://doi.org/10.1145/3539637.3557059","url":null,"abstract":"Mimesis is a term created by Aristotle and Plato in which art imitates life. Mimesis has been studied since ancient Greece and governed the theatrical and sculptural creations of the time. In this context, our work aims to study the effect of mimesis in the current cinematographic scenario, correlating historical events of the 20th and 21st centuries to the great cinematographic productions that follow. The question that guides our work is “Is there an increase in the release of films with a certain theme after a historical event?”. To answer this, we propose a methodology that uses two distinct data sources: one related to descriptions of historical facts from the 20th and 21st centuries extracted from Wikipedia and another with descriptions of films extracted from TMDb. Using topic modeling strategies, we automatically find the main themes related to historical events, and later, we evaluate how the description of a film is associated with the themes found. Temporal analysis is done to assess the popularity of each of the themes over time. In the results obtained by our methodology, there was a significant increase in the popularity of films that addressed themes related to historical events that occurred in an immediately preceding moment in time, corroborating the concept of mimesis.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132845322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Human pose estimation (HPE) is an important field of computer vision that aims to predict poses of individuals from videos and images. It has been used in many different areas including human-computer interaction, motion analysis, surveillance, action prediction, action correction, augmented reality, virtual reality, and healthcare. Executing movements correctly is crucial in all kinds of physical activities, both to increase performance and reduce risk of injury. HPE is poised to help athletes better analyse the quality of their movements. This work proposes a model for movement analysis, repetition count, and movement correction in physical exercises using HPE. For this purpose, a study is carried out in the field of HPE applied to sports and another study is focused on HPE for correction and postural analysis. From this, it is verified what is the state of the art in HPE for physical exercises and what is the best method for analyzing movements. This work implements an application with improvements in respect to other related work, focusing mainly on the feedback presented to the user when performing a certain movement. To validate the proposed model, a quantitative research was carried out using the Unified Theory of Acceptance and Use (UTAUT). For both people who exercise and professionals in the field of physical education, the results demonstrate that the application is able to analyze the biomechanics of movement, responding with speed and precision to execution errors. Among other results are: user satisfaction, interest in using the application in the future, and agreement in relation to good performance in helping and analyzing physical exercises.
{"title":"A Movement Analysis Application using Human Pose Estimation and Action Correction","authors":"Gisela Miranda Difini, M. G. Martins, J. Barbosa","doi":"10.1145/3539637.3557931","DOIUrl":"https://doi.org/10.1145/3539637.3557931","url":null,"abstract":"Human pose estimation (HPE) is an important field of computer vision that aims to predict poses of individuals from videos and images. It has been used in many different areas including human-computer interaction, motion analysis, surveillance, action prediction, action correction, augmented reality, virtual reality, and healthcare. Executing movements correctly is crucial in all kinds of physical activities, both to increase performance and reduce risk of injury. HPE is poised to help athletes better analyse the quality of their movements. This work proposes a model for movement analysis, repetition count, and movement correction in physical exercises using HPE. For this purpose, a study is carried out in the field of HPE applied to sports and another study is focused on HPE for correction and postural analysis. From this, it is verified what is the state of the art in HPE for physical exercises and what is the best method for analyzing movements. This work implements an application with improvements in respect to other related work, focusing mainly on the feedback presented to the user when performing a certain movement. To validate the proposed model, a quantitative research was carried out using the Unified Theory of Acceptance and Use (UTAUT). For both people who exercise and professionals in the field of physical education, the results demonstrate that the application is able to analyze the biomechanics of movement, responding with speed and precision to execution errors. Among other results are: user satisfaction, interest in using the application in the future, and agreement in relation to good performance in helping and analyzing physical exercises.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"504 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131677466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social media and online discussion platforms suffer from the prevalence of uncivil behavior, such as harassment and abuse, seeking to curb toxic comments. There are several approaches to classifying toxic comments automatically. Some of them have more resources and are more advanced in English, thus, stimulating the task of translating the text from a specific language to English. While researchers have shown evidence that this practice is indicated for certain tasks, such as sentiment analysis, little is known in the context of toxicity identification. In this research, we assess the performance of a freely available model for toxic language detection in online comments called Perspective API, widely adopted by some famous news media sites to identify different toxicity classes in online comments. For that, we obtained comments in Portuguese from two Brazilian news media websites during a politically polarized situation as a use case. Then, this dataset was translated to English and compared to four baseline datasets, two composed of highly toxic comments, one in Portuguese and other in English, and two composed of neutral comments, also one in Portuguese and other in English – all of them in its original language, not translated. Finally, human-annotated comments from the news comments dataset were analyzed to assess the scores provided by the Perspective API for the original and the translated versions. Results indicate that keeping the texts in their original language is preferable, even in comparing different languages. Nevertheless, if the translated version is strictly necessary, ways of dealing with the situation were suggested to preserve as much information as possible from the original version.
{"title":"Should We Translate? Evaluating Toxicity in Online Comments when Translating from Portuguese to English","authors":"Jordan K. Kobellarz, Thiago H. Silva","doi":"10.1145/3539637.3556892","DOIUrl":"https://doi.org/10.1145/3539637.3556892","url":null,"abstract":"Social media and online discussion platforms suffer from the prevalence of uncivil behavior, such as harassment and abuse, seeking to curb toxic comments. There are several approaches to classifying toxic comments automatically. Some of them have more resources and are more advanced in English, thus, stimulating the task of translating the text from a specific language to English. While researchers have shown evidence that this practice is indicated for certain tasks, such as sentiment analysis, little is known in the context of toxicity identification. In this research, we assess the performance of a freely available model for toxic language detection in online comments called Perspective API, widely adopted by some famous news media sites to identify different toxicity classes in online comments. For that, we obtained comments in Portuguese from two Brazilian news media websites during a politically polarized situation as a use case. Then, this dataset was translated to English and compared to four baseline datasets, two composed of highly toxic comments, one in Portuguese and other in English, and two composed of neutral comments, also one in Portuguese and other in English – all of them in its original language, not translated. Finally, human-annotated comments from the news comments dataset were analyzed to assess the scores provided by the Perspective API for the original and the translated versions. Results indicate that keeping the texts in their original language is preferable, even in comparing different languages. Nevertheless, if the translated version is strictly necessary, ways of dealing with the situation were suggested to preserve as much information as possible from the original version.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116853578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Thiago Silva, M. Cavalcanti, Felipe Melo Feliciano De Sá, Isaac Nóbrega Marinho, Daniel De Queiroz Cavalcanti, Valdecir Becker
Abstract: This article describes a brainwave visualization system using EEG and Eye Tracking in order to map the emotional relationship of individuals with audiovisual workpieces, especially attention and taste. Using the Design Science Research method, the artifact was specified, implemented and tested with 10 subjects, using a horror movie trailer. A preliminary and a post-test questionnaire was presented to the participants. The results indicate patterns of emotional identification with the film, which can be interpreted as an inclination to watch the film in movie theaters or a repulsion to the theme/genre of the film. In conclusion, this research points to an advance in evaluation of audiovisual workpieces, contemplating unconscious emotional elements of subjective perceptions about the watched content.
{"title":"Visualization of brainwaves using EEG to map emotions with eye tracking to identify attention in audiovisual workpieces","authors":"Thiago Silva, M. Cavalcanti, Felipe Melo Feliciano De Sá, Isaac Nóbrega Marinho, Daniel De Queiroz Cavalcanti, Valdecir Becker","doi":"10.1145/3539637.3557055","DOIUrl":"https://doi.org/10.1145/3539637.3557055","url":null,"abstract":"Abstract: This article describes a brainwave visualization system using EEG and Eye Tracking in order to map the emotional relationship of individuals with audiovisual workpieces, especially attention and taste. Using the Design Science Research method, the artifact was specified, implemented and tested with 10 subjects, using a horror movie trailer. A preliminary and a post-test questionnaire was presented to the participants. The results indicate patterns of emotional identification with the film, which can be interpreted as an inclination to watch the film in movie theaters or a repulsion to the theme/genre of the film. In conclusion, this research points to an advance in evaluation of audiovisual workpieces, contemplating unconscious emotional elements of subjective perceptions about the watched content.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123717140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heitor Werneck, N. Silva, Carlos Mito, A. Pereira, D. Dias, E. Albergaria, Leonardo Rocha
In online marketing environments, we have seen strong growth in the fashion domain, allowing consumers to access a worldwide network of brands. Despite the significant advances of the so-called Recommender Systems in more traditional scenarios, they still fail to offer a personalized and reliable fashion shopping experience that allows customers to discover products that suit their style and products that complement their choices or challenge them with new ideas. In this work, we propose a new ensemble recommendation system that combines different context information (customer-product interaction, item characteristics and user behaviour) with the predictions (recommendations) of different state-of-the-art traditional Recommender Systems to recognize new patterns in user-item interaction and to ensure a desirable level of personalization for fashion domains. Specifically, in the present work, we present a first instantiation that combines a collaborative filtering neural network method, a non-customized classical method and domain context information. In our experimental evaluation, considering two Amazon data collections, the instantiation of our proposal presented significant gains of up to 80% of MRR, 70% of NDCG and 108% of Hits compared with the methods considered state-of-the-art for the fashion recommendation scenario.
{"title":"Introducing Contextual Information in an Ensemble Recommendation System for Fashion Domains","authors":"Heitor Werneck, N. Silva, Carlos Mito, A. Pereira, D. Dias, E. Albergaria, Leonardo Rocha","doi":"10.1145/3539637.3557058","DOIUrl":"https://doi.org/10.1145/3539637.3557058","url":null,"abstract":"In online marketing environments, we have seen strong growth in the fashion domain, allowing consumers to access a worldwide network of brands. Despite the significant advances of the so-called Recommender Systems in more traditional scenarios, they still fail to offer a personalized and reliable fashion shopping experience that allows customers to discover products that suit their style and products that complement their choices or challenge them with new ideas. In this work, we propose a new ensemble recommendation system that combines different context information (customer-product interaction, item characteristics and user behaviour) with the predictions (recommendations) of different state-of-the-art traditional Recommender Systems to recognize new patterns in user-item interaction and to ensure a desirable level of personalization for fashion domains. Specifically, in the present work, we present a first instantiation that combines a collaborative filtering neural network method, a non-customized classical method and domain context information. In our experimental evaluation, considering two Amazon data collections, the instantiation of our proposal presented significant gains of up to 80% of MRR, 70% of NDCG and 108% of Hits compared with the methods considered state-of-the-art for the fashion recommendation scenario.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132014826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Expert finding is a subject of research in information retrieval and, often, is taken to mean expertise retrieval within a specific organization. The task involves finding an expert on a given topic of interest. Even though there are several proposals in the literature, they do not consider the context in which the given expertise is bound. This paper introduces an approach to inject context into existing expertise evidence based on data extracted from the evidence. Our motivation is to provide context when describing the expertise associated with a candidate expert, allowing a user to understand the results better and choose the best candidate for the task.
{"title":"Context injection in expert finding","authors":"Rodrigo Gonçalves, C. Dorneles","doi":"10.1145/3539637.3556995","DOIUrl":"https://doi.org/10.1145/3539637.3556995","url":null,"abstract":"Expert finding is a subject of research in information retrieval and, often, is taken to mean expertise retrieval within a specific organization. The task involves finding an expert on a given topic of interest. Even though there are several proposals in the literature, they do not consider the context in which the given expertise is bound. This paper introduces an approach to inject context into existing expertise evidence based on data extracted from the evidence. Our motivation is to provide context when describing the expertise associated with a candidate expert, allowing a user to understand the results better and choose the best candidate for the task.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131901861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
WhatsApp has many similarities with online social networks, as it allows connections between multiple people and massive communication by sharing content with your contacts and public groups, which brings people together to discuss a topic. Even though it is one of the most popular social media in the world, there is a lack of a systematic understanding of the Whatsapp ecosystem, especially when it comes to knowing the subjects discussed in public groups and how other users find/join those groups. In this direction, our goal is to investigate how public groups are shared on the Web and also map the main topics existing within this ecosystem. For this, we perform a large-scale collection, spanning four main sources on the Web for sharing groups, with more than 270k WhatsApp public groups, categorizing and analyzing this environment. Our results shed light on a large existence of groups focused on topics such as friendship, pop culture, stickers, sales, jobs, education, and even adult content suggesting the many uses of the WhatsApp tool. We also found key differences in groups according to the source where it was posted. Moreover, we discovered how group links work to persuade users from other platforms into the underground environment of WhatsApp. Malicious groups abuse its closed architecture and low moderation for illicit practices such as selling fake money and cloned cards. Furthermore, our analysis also found evidence of automated behavior in malicious group sharing. Finally, we discuss implications and measures that can be taken to address these issues.
{"title":"“Click Here to Join”: A Large-Scale Analysis of Topics Discussed by Brazilian Public Groups on WhatsApp","authors":"Daniel Kansaon, P. Melo, Fabrício Benevenuto","doi":"10.1145/3539637.3557056","DOIUrl":"https://doi.org/10.1145/3539637.3557056","url":null,"abstract":"WhatsApp has many similarities with online social networks, as it allows connections between multiple people and massive communication by sharing content with your contacts and public groups, which brings people together to discuss a topic. Even though it is one of the most popular social media in the world, there is a lack of a systematic understanding of the Whatsapp ecosystem, especially when it comes to knowing the subjects discussed in public groups and how other users find/join those groups. In this direction, our goal is to investigate how public groups are shared on the Web and also map the main topics existing within this ecosystem. For this, we perform a large-scale collection, spanning four main sources on the Web for sharing groups, with more than 270k WhatsApp public groups, categorizing and analyzing this environment. Our results shed light on a large existence of groups focused on topics such as friendship, pop culture, stickers, sales, jobs, education, and even adult content suggesting the many uses of the WhatsApp tool. We also found key differences in groups according to the source where it was posted. Moreover, we discovered how group links work to persuade users from other platforms into the underground environment of WhatsApp. Malicious groups abuse its closed architecture and low moderation for illicit practices such as selling fake money and cloned cards. Furthermore, our analysis also found evidence of automated behavior in malicious group sharing. Finally, we discuss implications and measures that can be taken to address these issues.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131793779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Miniaturization of computing devices allows everyday physical objects to communicate on a network through various ubiquitous media. In this scenario, smart things can socially interact autonomously with each other. In order to make this scenario a reality, this work presents the conception of a Conceptual Model for the dynamic management of the relationships established between intelligent objects, thus contributing to the consolidation of the Social Internet of Things. We designed a friendship recommendation and social circle composition approach that monitors interaction and highlights the most relevant objects for fulfilling requests. Additional contributions are: (i) simplification of the interaction process between objects; (ii) timely indication of friendship; and (iii) a structuring proposal for the social circle. The Link Analysis technique is the basis of the model implemented to identify connections between individuals and qualify interactions. In addition, the composition of the social circle is guided by the theory of social networks of the Organizational Network Analysis methodology, aiming to simplify indications of new friendships. Results of partial evaluations demonstrated the potential of the implemented model to correctly classify the interactions and roles of objects defined in the relationships. This validation leads to planned future work and the improvement of the implemented model.
{"title":"A conceptual model for autonomic relationships in the Social Internet of Things","authors":"Leandro Camargo, A. Pernas, A. Yamin","doi":"10.1145/3539637.3557928","DOIUrl":"https://doi.org/10.1145/3539637.3557928","url":null,"abstract":"Miniaturization of computing devices allows everyday physical objects to communicate on a network through various ubiquitous media. In this scenario, smart things can socially interact autonomously with each other. In order to make this scenario a reality, this work presents the conception of a Conceptual Model for the dynamic management of the relationships established between intelligent objects, thus contributing to the consolidation of the Social Internet of Things. We designed a friendship recommendation and social circle composition approach that monitors interaction and highlights the most relevant objects for fulfilling requests. Additional contributions are: (i) simplification of the interaction process between objects; (ii) timely indication of friendship; and (iii) a structuring proposal for the social circle. The Link Analysis technique is the basis of the model implemented to identify connections between individuals and qualify interactions. In addition, the composition of the social circle is guided by the theory of social networks of the Organizational Network Analysis methodology, aiming to simplify indications of new friendships. Results of partial evaluations demonstrated the potential of the implemented model to correctly classify the interactions and roles of objects defined in the relationships. This validation leads to planned future work and the improvement of the implemented model.","PeriodicalId":350776,"journal":{"name":"Proceedings of the Brazilian Symposium on Multimedia and the Web","volume":"2 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128146141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}