Tomislav Duricic, Dominik Kowald, M. Schedl, E. Lex
Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends with and shape our social circles. In this paper, we study homophily in an online music platform Last.fm regarding user preferences towards listening to mainstream (M), novel (N), or diverse (D) content. Furthermore, we draw comparisons with homophily based on listening profiles derived from artists users have listened to in the past, i.e., artist profiles. Finally, we explore the utility of users' artist profiles as well as features describing M, N, and D for the task of link prediction. Our study reveals that: (i) users with a friendship connection share similar music taste based on their artist profiles; (ii) on average, a measure of how diverse is the music two users listen to is a stronger predictor of friendship than measures of their preferences towards mainstream or novel content, i.e., homophily is stronger for D than for M and N; (iii) some user groups such as high-novelty-seekers (explorers) exhibit strong homophily, but lower than average artist profile similarity; (iv) using M, N and D achieves comparable results on link prediction accuracy compared with using artist profiles, but the combination of features yields the best accuracy results, and (v) using combined features does not add value if graph-based features such as common neighbors are available, making M, N, and D features primarily useful in a cold-start user recommendation setting for users with few friendship connections. The insights from this study will inform future work on social context-aware music recommendation, user modeling, and link prediction.
{"title":"My friends also prefer diverse music: homophily and link prediction with user preferences for mainstream, novelty, and diversity in music","authors":"Tomislav Duricic, Dominik Kowald, M. Schedl, E. Lex","doi":"10.1145/3487351.3492706","DOIUrl":"https://doi.org/10.1145/3487351.3492706","url":null,"abstract":"Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends with and shape our social circles. In this paper, we study homophily in an online music platform Last.fm regarding user preferences towards listening to mainstream (M), novel (N), or diverse (D) content. Furthermore, we draw comparisons with homophily based on listening profiles derived from artists users have listened to in the past, i.e., artist profiles. Finally, we explore the utility of users' artist profiles as well as features describing M, N, and D for the task of link prediction. Our study reveals that: (i) users with a friendship connection share similar music taste based on their artist profiles; (ii) on average, a measure of how diverse is the music two users listen to is a stronger predictor of friendship than measures of their preferences towards mainstream or novel content, i.e., homophily is stronger for D than for M and N; (iii) some user groups such as high-novelty-seekers (explorers) exhibit strong homophily, but lower than average artist profile similarity; (iv) using M, N and D achieves comparable results on link prediction accuracy compared with using artist profiles, but the combination of features yields the best accuracy results, and (v) using combined features does not add value if graph-based features such as common neighbors are available, making M, N, and D features primarily useful in a cold-start user recommendation setting for users with few friendship connections. The insights from this study will inform future work on social context-aware music recommendation, user modeling, and link prediction.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116392770","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}
Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event. We propose the MELANIE model, where an event is formulated as a Markov Decision Process, performing meta-learning on reinforcement learning tasks. By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections. To ensure fast adaptation to new connections or changes among viewers during an event, we implement a prioritized replay memory buffer based on the Kullback-Leibler divergence of the reward/throughput of the viewers' connections. Moreover, we adopt a model-agnostic meta-learning framework to generate a global model from past events. As viewers scarcely participate in several events, the challenge resides on how to account for the low structural similarity of different events. To combat this issue, we design a graph signature buffer to calculate the structural similarities of several streaming events and adjust the training of the global model accordingly. We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events. Our experiments demonstrate the effectiveness of our proposed model, with an average relative gain of 25% against state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/melanie
{"title":"Meta-reinforcement learning via buffering graph signatures for live video streaming events","authors":"Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas","doi":"10.1145/3487351.3490973","DOIUrl":"https://doi.org/10.1145/3487351.3490973","url":null,"abstract":"In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event. We propose the MELANIE model, where an event is formulated as a Markov Decision Process, performing meta-learning on reinforcement learning tasks. By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections. To ensure fast adaptation to new connections or changes among viewers during an event, we implement a prioritized replay memory buffer based on the Kullback-Leibler divergence of the reward/throughput of the viewers' connections. Moreover, we adopt a model-agnostic meta-learning framework to generate a global model from past events. As viewers scarcely participate in several events, the challenge resides on how to account for the low structural similarity of different events. To combat this issue, we design a graph signature buffer to calculate the structural similarities of several streaming events and adjust the training of the global model accordingly. We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events. Our experiments demonstrate the effectiveness of our proposed model, with an average relative gain of 25% against state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/melanie","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123712578","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}
Pub Date : 2021-10-01DOI: 10.1101/2021.09.29.21264175
S. Hurtado, R. Marculescu, J. Drake, R. Srinivasan
With the recent advances in human sensing, the push to integrate human mobility tracking with epidemic modeling highlights the lack of groundwork at the mesoscale (e.g., city-level) for both contact tracing and transmission dynamics. Although GPS data has been used to study city-level outbreaks in the past, existing approaches fail to capture the path of infection at the individual level. Consequently, in this paper, we extend epidemics prediction from estimating the size of an outbreak at the population level to estimating the individuals who may likely get infected within a finite period of time. To this end, we propose a network science based method to first build and then prune the dynamic contact networks for recurring interactions; these networks can serve as the backbone topology for mechanistic epidemics modeling. We test our method using Foursquare's Points of Interest (POI) smart phone geolocation data from over 1.3 million devices to better approximate the COVID-19 infection curves for two major (yet very different) US cities, (i.e., Austin and New York City), while maintaining the granularity of individual transmissions and reducing model uncertainty. Our method provides a foundation for building a disease prediction framework at the mesoscale that can help both policy makers and individuals better understand their estimated state of health and help the pandemic mitigation efforts.
{"title":"Pruning digital contact networks for meso-scale epidemic surveillance using foursquare data","authors":"S. Hurtado, R. Marculescu, J. Drake, R. Srinivasan","doi":"10.1101/2021.09.29.21264175","DOIUrl":"https://doi.org/10.1101/2021.09.29.21264175","url":null,"abstract":"With the recent advances in human sensing, the push to integrate human mobility tracking with epidemic modeling highlights the lack of groundwork at the mesoscale (e.g., city-level) for both contact tracing and transmission dynamics. Although GPS data has been used to study city-level outbreaks in the past, existing approaches fail to capture the path of infection at the individual level. Consequently, in this paper, we extend epidemics prediction from estimating the size of an outbreak at the population level to estimating the individuals who may likely get infected within a finite period of time. To this end, we propose a network science based method to first build and then prune the dynamic contact networks for recurring interactions; these networks can serve as the backbone topology for mechanistic epidemics modeling. We test our method using Foursquare's Points of Interest (POI) smart phone geolocation data from over 1.3 million devices to better approximate the COVID-19 infection curves for two major (yet very different) US cities, (i.e., Austin and New York City), while maintaining the granularity of individual transmissions and reducing model uncertainty. Our method provides a foundation for building a disease prediction framework at the mesoscale that can help both policy makers and individuals better understand their estimated state of health and help the pandemic mitigation efforts.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126019380","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}
Natural disasters continue to cause tremendous damage to human lives and properties. The Philippines, due to its geographic location, is considered a natural disaster-prone country experiencing an average of 20 tropical cyclones annually. Understanding what factors significantly affect decision making during crucial evacuation stages could help in making decisions on how to prepare for disasters, how to act appropriately and strategically respond during and after a calamity. In this work, an agent-based model for preemptive evacuation decisions during typhoon is presented. In the model, civilians are represented by households and their evacuation decisions were based from calculated perceived risk. Also, rescuer and shelter manager agents were included as facilitators during the preemptive evacuation process. National and municipal census data were employed in the model, particularly for the demographics of household agents. Further, geospatial data of a village in a typhoon-susceptible municipality was used to represent the environment. The decision to evacuate or not to evacuate depends on the agent's perceived risk which also depends on three decision factors: characteristics of the decision maker (CDM); capacity related factors (CRF); and hazard related factors (HRF). Finally, the number of households who decided to evacuate or opted to stay as influenced by the model's decision factors were determined during simulations. Sensitivity analysis using linear regression shows that all parameters used in the model are significant in the evacuation decision of household agents.
{"title":"A spatial agent-based model for preemptive evacuation decisions during typhoon","authors":"Rey C. Rodrigueza, Maria Regina Justina E. Estuar","doi":"10.1145/3487351.3488338","DOIUrl":"https://doi.org/10.1145/3487351.3488338","url":null,"abstract":"Natural disasters continue to cause tremendous damage to human lives and properties. The Philippines, due to its geographic location, is considered a natural disaster-prone country experiencing an average of 20 tropical cyclones annually. Understanding what factors significantly affect decision making during crucial evacuation stages could help in making decisions on how to prepare for disasters, how to act appropriately and strategically respond during and after a calamity. In this work, an agent-based model for preemptive evacuation decisions during typhoon is presented. In the model, civilians are represented by households and their evacuation decisions were based from calculated perceived risk. Also, rescuer and shelter manager agents were included as facilitators during the preemptive evacuation process. National and municipal census data were employed in the model, particularly for the demographics of household agents. Further, geospatial data of a village in a typhoon-susceptible municipality was used to represent the environment. The decision to evacuate or not to evacuate depends on the agent's perceived risk which also depends on three decision factors: characteristics of the decision maker (CDM); capacity related factors (CRF); and hazard related factors (HRF). Finally, the number of households who decided to evacuate or opted to stay as influenced by the model's decision factors were determined during simulations. Sensitivity analysis using linear regression shows that all parameters used in the model are significant in the evacuation decision of household agents.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117008811","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}
Anish K. Vallapuram, Nikhil Nanda, Young D. Kwon, Pan Hui
The survival of a business is undeniably pertinent to its success. A key factor contributing to its continuity depends on its customers. The surge of location-based social networks such as Yelp, Diangping, and Foursquare has paved the way for leveraging user-generated content on these platforms to predict business survival. Prior works in this area have developed several quantitative features to capture geography and user mobility among businesses. However, the development of qualitative features is minimal. In this work, we thus perform extensive feature engineering across four feature sets, namely, geography, user mobility, business attributes, and linguistic modelling to develop classifiers for business survival prediction. We additionally employ an interpretability framework to generate explanations and qualitatively assess the classifiers' predictions. Experimentation among the feature sets reveals that qualitative features including business attributes and linguistic features have the highest predictive power, achieving AUC scores of 0.72 and 0.67, respectively. Furthermore, the explanations generated by the interpretability framework demonstrate that these models can potentially identify the reasons from review texts for the survival of a business.
{"title":"Interpretable business survival prediction","authors":"Anish K. Vallapuram, Nikhil Nanda, Young D. Kwon, Pan Hui","doi":"10.1145/3487351.3488353","DOIUrl":"https://doi.org/10.1145/3487351.3488353","url":null,"abstract":"The survival of a business is undeniably pertinent to its success. A key factor contributing to its continuity depends on its customers. The surge of location-based social networks such as Yelp, Diangping, and Foursquare has paved the way for leveraging user-generated content on these platforms to predict business survival. Prior works in this area have developed several quantitative features to capture geography and user mobility among businesses. However, the development of qualitative features is minimal. In this work, we thus perform extensive feature engineering across four feature sets, namely, geography, user mobility, business attributes, and linguistic modelling to develop classifiers for business survival prediction. We additionally employ an interpretability framework to generate explanations and qualitatively assess the classifiers' predictions. Experimentation among the feature sets reveals that qualitative features including business attributes and linguistic features have the highest predictive power, achieving AUC scores of 0.72 and 0.67, respectively. Furthermore, the explanations generated by the interpretability framework demonstrate that these models can potentially identify the reasons from review texts for the survival of a business.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128940798","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}
Network inference is the process of deciding what is the true unknown graph underlying a set of interactions between nodes. There is a vast literature on the subject, but most known methods have an important drawback: the inferred graph is not guaranteed to explain every interaction from the input trace. We consider this an important issue since such inferred graph cannot be used as input for applications that require a reliable estimate of the true graph. On the other hand, a graph having trace feasibility guarantees can help us better understand the true (hidden) interactions that may have taken place between nodes of interest. The inference of such graph is the goal of this paper. Firstly, given an activity log from a social network, we introduce a set of constraints that take into consideration all the hidden paths that are possible between the nodes of the trace, given their timestamps of interaction. Then, we develop a nontrivial modification of the Expectation-Maximization algorithm by Newman [1], that we call Constrained-EM, which incorporates the constraints and a set of auxiliary variables into the inference process to guide it towards the feasibility of the trace. Experimental results on real-world data from Twitter confirm that Constrained-EM generates a posterior distribution of graphs that explains all the events observed in the trace while presenting the desired properties of a scale-free, small-world graph. Our method also outperforms established methods in terms of feasibility and quality of the inferred graph.
{"title":"Bayesian inference of a social graph with trace feasibility guarantees","authors":"Effrosyni Papanastasiou, A. Giovanidis","doi":"10.1145/3487351.3488279","DOIUrl":"https://doi.org/10.1145/3487351.3488279","url":null,"abstract":"Network inference is the process of deciding what is the true unknown graph underlying a set of interactions between nodes. There is a vast literature on the subject, but most known methods have an important drawback: the inferred graph is not guaranteed to explain every interaction from the input trace. We consider this an important issue since such inferred graph cannot be used as input for applications that require a reliable estimate of the true graph. On the other hand, a graph having trace feasibility guarantees can help us better understand the true (hidden) interactions that may have taken place between nodes of interest. The inference of such graph is the goal of this paper. Firstly, given an activity log from a social network, we introduce a set of constraints that take into consideration all the hidden paths that are possible between the nodes of the trace, given their timestamps of interaction. Then, we develop a nontrivial modification of the Expectation-Maximization algorithm by Newman [1], that we call Constrained-EM, which incorporates the constraints and a set of auxiliary variables into the inference process to guide it towards the feasibility of the trace. Experimental results on real-world data from Twitter confirm that Constrained-EM generates a posterior distribution of graphs that explains all the events observed in the trace while presenting the desired properties of a scale-free, small-world graph. Our method also outperforms established methods in terms of feasibility and quality of the inferred graph.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130424377","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}
Behnaz Moradi-Jamei, Brandon L. Kramer, J. Bayo´an, Santiago Calder´on, Gizem Korkmaz
This paper studies community formation in OSS collaboration networks. While most current work examines the emergence of small-scale OSS projects, our approach draws on a large-scale historical dataset of 1.8 million GitHub users and their repository contributions. OSS collaborations are characterized by small groups of users that work closely together, leading to the presence of communities defined by short cycles in the underlying network structure. To understand the impact of this phenomenon, we apply a pre-processing step that accounts for the cyclic network structure by using Renewal-Nonbacktracking Random Walks (RNBRW) and the strength of pairwise collaborations before implementing the Louvain method to identify communities within the network. Equipping Louvain with RNBRW and the contribution strength provides a more assertive approach for detecting small-scale teams and reveals nontrivial differences in community detection such as users' tendencies toward preferential attachment to more established collaboration communities. Using this method, we also identify key factors that affect community formation, including the effect of users' location and primary programming language, which was determined using a comparative method of contribution activities. Overall, this paper offers several promising methodological insights for both open-source software experts and network scholars interested in studying team formation.
{"title":"Community formation and detection on GitHub collaboration networks","authors":"Behnaz Moradi-Jamei, Brandon L. Kramer, J. Bayo´an, Santiago Calder´on, Gizem Korkmaz","doi":"10.1145/3487351.3488278","DOIUrl":"https://doi.org/10.1145/3487351.3488278","url":null,"abstract":"This paper studies community formation in OSS collaboration networks. While most current work examines the emergence of small-scale OSS projects, our approach draws on a large-scale historical dataset of 1.8 million GitHub users and their repository contributions. OSS collaborations are characterized by small groups of users that work closely together, leading to the presence of communities defined by short cycles in the underlying network structure. To understand the impact of this phenomenon, we apply a pre-processing step that accounts for the cyclic network structure by using Renewal-Nonbacktracking Random Walks (RNBRW) and the strength of pairwise collaborations before implementing the Louvain method to identify communities within the network. Equipping Louvain with RNBRW and the contribution strength provides a more assertive approach for detecting small-scale teams and reveals nontrivial differences in community detection such as users' tendencies toward preferential attachment to more established collaboration communities. Using this method, we also identify key factors that affect community formation, including the effect of users' location and primary programming language, which was determined using a comparative method of contribution activities. Overall, this paper offers several promising methodological insights for both open-source software experts and network scholars interested in studying team formation.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117002427","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}
A. Saxena, Yulong Pei, Jan Veldsink, Werner van Ipenburg, G. Fletcher, Mykola Pechenizkiy
We construct a network of 1.6 million nodes from banking transactions of users of Rabobank. We assign two weights on each edge, which are the aggregate transferred amount and the total number of transactions between the users from the year 2010 to 2020. We present a detailed analysis of the unweighted and both weighted networks by examining their degree, strength, and weight distributions, as well as the topological assortativity and weighted assortativity, clustering, and weighted clustering, together with correlations between these quantities. We further study the meso-scale properties of the networks and compare them to a randomized reference system. This will be the first publicly shared dataset of intra-bank transactions, and this work highlights the unique characteristics of banking transaction networks with other scale-free networks.
{"title":"The banking transactions dataset and its comparative analysis with scale-free networks","authors":"A. Saxena, Yulong Pei, Jan Veldsink, Werner van Ipenburg, G. Fletcher, Mykola Pechenizkiy","doi":"10.1145/3487351.3488339","DOIUrl":"https://doi.org/10.1145/3487351.3488339","url":null,"abstract":"We construct a network of 1.6 million nodes from banking transactions of users of Rabobank. We assign two weights on each edge, which are the aggregate transferred amount and the total number of transactions between the users from the year 2010 to 2020. We present a detailed analysis of the unweighted and both weighted networks by examining their degree, strength, and weight distributions, as well as the topological assortativity and weighted assortativity, clustering, and weighted clustering, together with correlations between these quantities. We further study the meso-scale properties of the networks and compare them to a randomized reference system. This will be the first publicly shared dataset of intra-bank transactions, and this work highlights the unique characteristics of banking transaction networks with other scale-free networks.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127108387","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 outbreak of COVID-19 has resulted in an "infodemic" that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.
{"title":"MMCoVaR: multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification","authors":"Mingxuan Chen, Xinqiao Chu, K. P. Subbalakshmi","doi":"10.1145/3487351.3488346","DOIUrl":"https://doi.org/10.1145/3487351.3488346","url":null,"abstract":"The outbreak of COVID-19 has resulted in an \"infodemic\" that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125095043","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}
Due to the over-emphasize of the quantity of data, the data quality has often been overlooked. However, not all training data points contribute equally to learning. In particular, if mislabeled, it might actively damage the performance of the model and the ability to generalize out of distribution, as the model might end up learning spurious artifacts present in the dataset. This problem gets compounded by the prevalence of heavily parameterized and complex deep neural networks, which can, with their high capacity, end up memorizing the noise present in the dataset. This paper proposes a novel statistic - noise score, as a measure for the quality of each data point to identify such mislabeled samples based on the variations in the latent space representation. In our work, we use the representations derived by the inference network of data quality supervised variational autoencoder (AQUAVS). Our method leverages the fact that samples belonging to the same class will have similar latent representations. Therefore, by identifying the outliers in the latent space, we can find the mislabeled samples. We validate our proposed statistic through experimentation by corrupting MNIST, FashionMNIST, and CIFAR10/100 datasets in different noise settings for the task of identifying mislabelled samples. We further show significant improvements in accuracy for the classification task for each dataset.
{"title":"Assessing the quality of the datasets by identifying mislabeled samples","authors":"Vaibhav Pulastya, Gaurav Nuti, Yash Kumar Atri, Tanmoy Chakraborty","doi":"10.1145/3487351.3488361","DOIUrl":"https://doi.org/10.1145/3487351.3488361","url":null,"abstract":"Due to the over-emphasize of the quantity of data, the data quality has often been overlooked. However, not all training data points contribute equally to learning. In particular, if mislabeled, it might actively damage the performance of the model and the ability to generalize out of distribution, as the model might end up learning spurious artifacts present in the dataset. This problem gets compounded by the prevalence of heavily parameterized and complex deep neural networks, which can, with their high capacity, end up memorizing the noise present in the dataset. This paper proposes a novel statistic - noise score, as a measure for the quality of each data point to identify such mislabeled samples based on the variations in the latent space representation. In our work, we use the representations derived by the inference network of data quality supervised variational autoencoder (AQUAVS). Our method leverages the fact that samples belonging to the same class will have similar latent representations. Therefore, by identifying the outliers in the latent space, we can find the mislabeled samples. We validate our proposed statistic through experimentation by corrupting MNIST, FashionMNIST, and CIFAR10/100 datasets in different noise settings for the task of identifying mislabelled samples. We further show significant improvements in accuracy for the classification task for each dataset.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116006046","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：