Soc2Net: International workshop on Modeling and mining Social-Media-driven Complex Networks @ ICWSM-19
June 11, 2019, Munich, Germany
The growing availability of multi-faceted social media data gives rise to unprecedented opportunities for unveiling complex real-world online behaviors. This also supports the proliferation of complex network models where the expressive power of the graph-based relational structure is enhanced through exposing several types of features that are peculiar of the social media platforms. This workshop aims to explore innovative methods that are designed to improve our understanding of behaviors and relations underlying feature-rich networks built upon social media, here called social-media-driven complex networks. Exemplary network models of such kind include heterogeneous, multilayer/multiplex/multirelational networks, temporal, location-aware, and probabilistic networks, and any other type of data-driven network that can be inferred from social media data contexts.
The aim of the Soc2Net workshop, that will be held in conjunction with The 13th International AAAI Conference on Web and Social Media (ICWSM-2019) in Munich (Germany), is to bring together researchers and practitioners from around the world interested in 1) exploring different perspectives and approaches to mine social-media-driven complex networks, 2) analyzing user behavior and evolution in social-media-driven complex networks, and 3) building models and frameworks for evaluating the respective approaches.
Authors are encouraged to evaluate their models, methods, metrics and algorithms on real-world social networks built upon publicly available datasets, e.g., relying on the datasets from the previous editions of ICWSM which are released as openly available community resources. We solicit interdisciplinary submissions focusing on topics of interest to different research communities, including social science, economics and digital humanities.
Robert West: Message Distortion in Information Cascades
Information diffusion is usually modeled as a process in which immutable pieces of information propagate over a network. In reality, however, messages are not immutable, but may be morphed with every step, potentially entailing large cumulative distortions. This process may lead to misinformation even in the absence of malevolent actors, and understanding it is crucial for modeling and improving online information systems. Here, we perform a controlled, crowdsourced experiment in which we simulate the propagation of information from medical research papers. Starting from the original abstracts, crowd workers iteratively shorten previously produced summaries to increasingly smaller lengths. We also collect control summaries where the original abstract is compressed directly to the final target length. Comparing cascades to controls allows us to separate the effect of the length constraint from that of accumulated distortion. Via careful manual coding, we annotate lexical and semantic units in the medical abstracts and track them along cascades. We find that iterative summarization has a negative impact due to the accumulation of error, but that high-quality intermediate summaries result in less distorted messages than in the control case. Different types of information behave differently; in particular, the conclusion of a medical abstract (i.e., its key message) is distorted most. Finally, we compare extractive with abstractive summaries, finding that the latter are less prone to semantic distortion. Overall, this work is a first step in studying information cascades without the assumption that disseminated content is immutable, with implications on our understanding of the role of word-of-mouth effects on the misreporting of science. (Joint work with Manoel Horta Ribeiro and Kristina Gligoric)
Robert West is an assistant professor of Computer Science at EPFL, where he heads the Data Science Lab. His research aims to understand, predict, and enhance human behavior in social and information networks by developing techniques in data science, data mining, network analysis, machine learning, and natural language processing. He holds a PhD in computer science from Stanford University.