CMN 150V Midterm 1 Exam 2026/2027 | 150+ Questions & Answers | Computational Social Science, Big Data, Networks, AI & Machine Learning

This comprehensive CMN 150V Midterm #1 2026/2027 study document contains 150+ exam-style questions and correct answers covering computational social science, the digital revolution, big data, social networks, artificial intelligence, machine learning, computational communication, and digital footprints. The 38-page resource begins with the transition from traditional empirical and theoretical approaches toward computational science, examining induction and deduction, emergence, complexity, digital traces, scientific modeling, nonlinear social processes, and the limitations of predicting complex social dynamics from historical data. The document provides extensive coverage of big data and computational social science, including data fusion, metadata, sampling and representativeness, digital-footprint bias, filter bubbles, echo chambers, Natural Language Processing (NLP), predictive policing, correlation versus causation, feature engineering, and supervised machine learning. Case studies and examples address Google Flu Trends, mobile-phone data and wealth prediction in Rwanda, agricultural and climate data in Colombia, recommendation systems, machine translation, and the use of digital traces as complementary sources for traditional social-science research. A substantial section focuses on social network analysis, covering homophily, social influence, relationship strength, nodes, links, multi-node and multiplex networks, Granovetter’s strength of weak ties, degrees of separation, cliques, clustering coefficients, modularity, community detection, degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, PageRank, paths, cycles, geodesics, network diameter, and average path length. The material connects these concepts to social influence, health, generosity, innovation diffusion, and large-scale social experiments. The AI and machine-learning material reviews the Turing Test, AI winter, the importance of large datasets, traditional programming versus machine learning, regression, generalizability, model complexity, overfitting, regularization, parameters and hyperparameters, and the proper separation of training, validation, and testing datasets. Later sections extend computational methods to fake-news detection, moral framing, computational sentiment analysis, brain-as-predictor research, speech segmentation, first-language acquisition, Bayesian inference, computational cognitive models, dialogue systems, collaborative and content-based filtering, emotion and sarcasm detection, and educational applications of conversational systems. The document is particularly relevant to students studying CMN 150V and computational social science at the University of California, Davis, as well as students reviewing interdisciplinary applications of communication, data science, social networks and machine learning. The source material itself references UC Davis professors and course examples throughout, including work on computational communication and dialogue systems. Relevant Students: CMN 150V students, UC Davis Communication students, computational social science students, communication majors, data science students, social network analysis students, digital media students, computational communication students, artificial intelligence students, machine learning beginners, sociology students using computational methods, and students preparing for CMN 150V Midterm #1. Keywords: CMN 150V Midterm 1, CMN 150V exam 2026, CMN 150V exam 2027, CMN 150V questions and answers, CMN 150V study guide, computational social science, computational communication, big data, digital revolution, digital footprint, digital trace data, data fusion, metadata, sampling bias, social network analysis, network science, homophily, strength of weak ties, degrees of separation, network centrality, betweenness centrality, closeness centrality, eigenvector centrality, PageRank, community detection, artificial intelligence, machine learning, supervised machine learning, regression analysis, overfitting, regularization, training set, validation set, testing set, generalizability, feature engineering, Natural Language Processing, NLP, filter bubbles, echo chambers, predictive policing, correlation and causation, Bayesian inference, computational sentiment analysis, dialogue systems, UC Davis Communication