Suchergebnisse

AbstractMost of the current complex networks that are of interest to practitioners possess a certain community structure that plays an important role in understanding the properties of these networks. For instance, a closely connected social communities exhibit faster rate of transmission of information in comparison to loosely connected communities. Moreover, many machine learning algorithms and tools that are developed for complex networks try to take advantage of the existence of communities to improve their performance or speed. As a result, there are many competing algorithms for detecting communities in large networks. Unfortunately, these algorithms are often quite sensitive and so they cannot be fine-tuned for a given, but a constantly changing, real-world network at hand. It is therefore important to test these algorithms for various scenarios that can only be done using synthetic graphs that have built-in community structure, power law degree distribution, and other typical properties observed in complex networks. The standard and extensively used method for generating artificial networks is the LFR graph generator. Unfortunately, this model has some scalability limitations and it is challenging to analyze it theoretically. Finally, the mixing parameter μ, the main parameter of the model guiding the strength of the communities, has a non-obvious interpretation and so can lead to unnaturally defined networks. In this paper, we provide an alternative random graph model with community structure and power law distribution for both degrees and community sizes, the Artificial Benchmark for Community Detection (ABCD graph). The model generates graphs with similar properties as the LFR one, and its main parameter ξ can be tuned to mimic its counterpart in the LFR model, the mixing parameter μ. We show that the new model solves the three issues identified above and more. In particular, we test the speed of our algorithm and do a number of experiments comparing basic properties of both ABCD and LFR. The conclusion is that these models produce graphs with comparable properties but ABCD is fast, simple, and can be easily tuned to allow the user to make a smooth transition between the two extremes: pure (independent) communities and random graph with no community structure.

AbstractGraph embedding is a transformation of nodes of a network into a set of vectors. A good embedding should capture the underlying graph topology and structure, node-to-node relationship, and other relevant information about the graph, its subgraphs, and nodes themselves. If these objectives are achieved, an embedding is a meaningful, understandable, and often compressed representation of a network. Unfortunately, selecting the best embedding is a challenging task and very often requires domain experts. In this paper, we extend the framework for evaluating graph embeddings that was recently introduced in [15]. Now, the framework assigns two scores, local and global, to each embedding that measure the quality of an evaluated embedding for tasks that require good representation of local and, respectively, global properties of the network. The best embedding, if needed, can be selected in an unsupervised way, or the framework can identify a few embeddings that are worth further investigation. The framework is flexible and scalable and can deal with undirected/directed and weighted/unweighted graphs.

Intro -- Acknowledgments -- Contents -- 1 Introduction -- 2 Ontologies and Data Models for Cross-platform Social Media Data -- 2.1 Data Models for Social Media Data Analysis -- Homophily Analysis -- Social Identity Linkage -- Personality Analysis -- 2.2 Ontologies for Social Media Data -- Ontologies for Sentiment Analysis -- Ontologies for Situational Awareness -- 2.3 Potential Future Research Topics -- Metadata -- Federated Learning -- 3 Methods for Text Generation in NLP -- 3.1 Introduction -- 3.2 Past Approaches -- 3.3 GANs in NLP -- Reinforcement learning strategies -- Operating on continuous representations instead of discrete symbols -- Gumbel-softmax -- 3.4 Large Neural Language Models (LNLMs or LLMs) -- The Transformer and BERT -- BERT variants -- Introduction to GPT-3 -- 3.5 Dangers of E ective Generative LLMs -- Marginalized Group and Gender Bias -- Generation of Hateful Content -- De-biasing Approaches -- Environmental and Financial Impacts -- Identifying Information Extraction Attacks -- Simpler Approaches -- Potential Research Direction # 1 (Large Neural Language Models) -- 3.6 Detecting Generated Text -- Overview -- Detection of Machine-Generated Text -- The Issue with Simple Detection -- Detection of Fake News Content -- Issues of Comparison and Dataset Standardization -- Content-based Approaches -- Social-response-based Approaches -- Hybrid Approaches -- Graph-based Approaches -- Multimodal Approaches: Incorporating Visual Information -- Potential Research Direction # 2 (Fake News Detection) -- 4 Topic and Sentiment Modelling for Social Media -- 4.1 Introduction -- 4.2 Introduction to Topic Modelling -- 4.3 Overview of Classical Approaches to Topic Modelling -- LDA -- 4.4 Neural Topic Modelling -- Variational Topic Modelling -- LDA2Vec -- Top2Vec -- Use of Pre-trained Embeddings for Neural Topic Modelling.

This book provides a broad overview of the state of the art of the research in generative methods for the analysis of social media data. It especially includes two important aspects that currently gain importance in mining and modelling social media: dynamics and networks. Throughout the book, open problems, highlighting potential future directions, are clearly identified. The book aims at researchers and graduate students in social media analysis, information retrieval, and machine learning applications.--