Syllabus and Textbooks
The required reading will be from the following list as well as select journal/conference articles (see below) which are available online to UML students:
Syllabus
Prior to every class, we provide a list of Spotlight Papers - select research papers relevant to a specific lecture. Students are encouraged to read these papers before the class. See further details in Policies section.
W01, Sep 2 | Introduction and Basics: course overview, connectivity, bfs, shortest path, bipartite graphs | Slide 0,1,2,3 |
Ch.01 Overview [NCM] Ch.10.1 Social Networks as Graphs [MMD] Ch.02 Graphs [NCM] Ch.22 Elementary Graph Algorithms [CLRS] Ch.24 Single-Source Shortest Paths [CLRS] | What is Twitter, a social network or a news media? Kwak, H., et al. WWW’10 Understanding the demographics of twitter users. Mislove, A., et al. AAAI’11 TED talk: The birth of a word. Roy, D. 2011. | |
W02, Sep 9 | Strong and Weak Ties: centrality, betweenness, graph clustering | Slide 1,2 |
Ch.03 Strong and Weak Ties [NCM] Ch.07, 10.2 Clustering [MMD] Ch.04 Community Discovery [SNA] Ch.07 Social Influence [SNA] | Community detection in graphs. Fortunato, S. Physics reports’10 Structure and tie strengths in mobile communication networks. Onnela, J.P., et al. PNAS’07. Searching for superspreaders of information in real-world social media. Pei, S., et al. Scientific reports’14. Fragile online relationship: a first look at unfollow dynamics in twitter. Kwak, H., et al. SIGCHI’11. | |
W03, Sep 16 | Node Analysis: node similarity, homophily, and link prediction | Slide 1,2 |
Ch.04 Nets in Surrounding Context [NCM] Ch.09 Link Prediction [SNA] | Group formation in large social networks: membership, growth, and evolution. Backstrom, L., et al. SIGKDD’06. Feedback effects between similarity and social influence in online communities. Crandall, D., et al. SIGKDD’08. Empirical analysis of an evolving social network. Kossinets, G. and Watts, D.J. Science’06. How to hide one's relationships from link prediction algorithms. Waniek, M., et al. Scientific reports’19. | |
W04, Sep 23 | Web Graph and Network Popularity: connected components, bow-tie structure, power Law | Slide 1,2,3 |
Ch.13 The Structure of the Web [NCM] Ch.18 Power Laws [NCM] Ch.18 Rich-Get-Richer Phenomena [NCM] | Finding strongly connected components Inequality and unpredictability in an artificial cultural market. Salganik, M.J., et al. Science’06. Network structure from rich but noisy data. Newman, M.E.J. Nature Physics’18. Graph structure in the web. Broder, A., et al. Computer networks’00. | |
W05, Sep 30 | Information Cascading: information diffusion and basic cascade model | Slide 1,2,3 |
Ch.16 Information Cascades [NCM] Ch.19 Cascading Behavior in Networks [NCM] | Do cascades recur? Cheng, J., et al. WWW’16. Multi-winner contests for strategic diffusion in social networks. Shen, W., et al. AAAI’19. Lecture: Information diffusion on Twitter. Nikolov, S. 2012. TED talk: How to start a movement. Sivers, D. 2010. | |
W06, Oct 7 | Small world Phenomenon: six degree separation, decentralized search, HITS and PageRank | Slide 1,2 |
Ch.20 The Small-World Phenomenon [NCM] Ch.14 Link Analysis and Web search [NCM] Ch.05 Link Analysis [MMD] | The anatomy of the facebook social graph. Ugander, J., et al. arXiv’11. Four degrees of separation . Backstrom L., et al. WebSci’12. The small world problem . Milgram S. Psychology Today’1967. Documentary: Connected: the power of six degrees. A documentary on networks, social and otherwise. 2008. | |
W07, Oct 14 | Midterm exam! | |
Midterm exam | | |
W08, Oct 21 | Representation Learning 1: texts | Slide 0,1,2 |
| A neural probabilistic language model. Bengio, Yoshua, et al. JMLR’03. Distributed representations of words and phrases and their compositionality. Mikolov, T., et al. NIPS’13. Glove: global vectors for word representation. Pennington, J., et al. EMNLP’14. Retrofitting word vectors to semantic lexicons. Faruqui, M., et al. NAACL’15. AI2 talk: Beyond the Distributional Hypothesis: Learning Better Word Representations. Manaal F. 2016. | |
W09, Oct 28 | Representation Learning 2: graphs | Slide 1,2,3,4 |
| Deepwalk: online learning of social representations. Perozzi, B., et al. SIGKDD’14. Node2vec: scalable feature learning for networks. Grover, A. and Leskovec, J. SIGKDD’16. Learning convolutional neural networks for graphs. Niepert, M., et al. ICML’16. Inductive representation learning on large graphs. Hamilton, W., et al. NIPS’17. Semi-supervised classification with graph convolutional networks. Kipf, T.N., et al. ICLR’17. Course Lecture: Graph Representation Learning. Leskovec J. 2019. | |
W10, Nov 4 | Health Informatics: digital epidemiology and food computing | |
Guest Lectures: Emily Alsentzer, MIT & Harvard Mandy Korpusik, LMU | Estimating county health statistics with twitter. Culotta, A. CHI’14. Normalising medical concepts in social media texts by learning semantic representation. Limsopatham, N., et al. ACL’16. Semantic mapping of natural language input to database entries via CNNs. Korpusik, M., et al. ICASSP’17. Toward large-scale and multi-facet analysis of first-person alcohol drinking. Amiri, H., et al. AMIA’18 Machine learning in medicine. Rajkomar, A., et al. NEJM’19.
| |
W11, Nov 11 | Veterans Day | |
No class | | |
W12, Nov 18 | Network Analysis of Language: redundancy, specificity, churn, and polarization | |
| Linguistic redundancy in twitter. Zanzotto, F.M., et al. EMNLP’11. Global connectivity and multilinguals in the Twitter network. Hale, S.A. SIGCHI’14. Short text representation for detecting churn in microblogs. Amiri, H. and Daumé III, H. AAAI’16. Analyzing polarization in social media. Demszky, D., et al. NAACL’19. Predicting and analyzing language specificity in social media posts. Gao, Yifan, et al. AAAI’19.
| |
W13, Nov 25 | Thanksgiving | |
No class | | |
W14, Dec 2 | Search and Factuality: microblog search, moment retrieval, and fact checking | |
Guest Lecture: TBA | Overview of the trec-2014 microblog track. Lin J., et al. TREC’14. Attentive moment retrieval in videos. Liu, M., et al. SIGIR’18. Automatic stance detection using end-to-end memory networks. Mohtarami, M., et al. NAACL’18. Integrating video retrieval and moment detection in a unified corpus for video QA. Luo H., et al. InterSpeech’19. Contrastive language adaptation for cross-lingual stance detection. Mohtarami, M., et al. EMNLP’19.
| |
W15, Dec 9 | Project presentations | |
Project presentations. | |
|
|