A Reading List

For some of our perspective, follow the links...

The life-blood of the web is contained in its links. The best links are those which are freely given, where the author uses his or her expertise to make judicious recommendations of the best content out there on the web relating to the topic of their site. Here are some from us - a reading list of the books and papers we know and love.

Data Visualisation

• Information Visualisation: Perception for Design: a great foundational textbook on the psychology and applied science of data visualisation. A detailed exploration of how we see, and how that affects how we think. Ware, C. 2013. 3rd ed., Morgan Kaufmann/Elsevier.
• Visualize This: the FlowingData Guide to Design, Vizualisation, and Statisics: an excellent practical guide to both analysis and storytelling using data. Plenty of practical examples of using desktop tools such as Excel and Tableau; online tools such as ManyEyes, Wordle and FlowingData; programming languages such as python, R and processing; javascript libraries such as Protovis and d3. An excellent starting point for any budding data visualisation professional. Yau, N. 2011. Wiley.
• Visual Complexity: Mapping Patterns of Information: a detailed consideration of the new visual language being used by scientists to visualise highly complex network information - online social graphs, protein interactions, political donations, terrorist activities and affiliations, flight and traffic visualisations, bird flocking, neuron mapping, galaxy and quasar formation. Discusses the syntax of this new language, and attepts a little future gazing too. Inspiring stuff. Lima, M. 2011. Princeton Architectural Press.
• Beautiful Visualization: looking at Data Through the Eyes of Experts: expert essays from practitioners on how the approached particular visualisation problems. The experts are drawn from a variety of disciplines - art, design, science, statistics, politics, journalism. Eds. Steele J & Iliinsky N. 2010. 1st ed., O'Reilly.
• Information is Beautiful: the emphasis is here on beauty (or, perhaps, storytelling) over information, but that's not to say it isn't well worth a read. McCandless' work will be recognised by any regular readers of the Guardian newspaper or Wired magazine, and not all are quite as careful with their use of representation as a Tuftian purist might want. Nevertheless, McCandless's book (sold as 'A Visual Miscellaneum' in the US) is a great source of inspiration for data journalists and communication-minded scientists alike. McCandless, D. 2009. Collins.
• Now you see it: a more accessible introduction to visual quantitative data analysis than Colin Ware (and references Ware liberally), from a man who has made his career around designing graphs and dashboards. Few, S. 2009. Analytics Press.
• The Visual Display of Quantitative Information: a clear, beautifully presented philosophy of data visualisation. Don't think it's just musings on perfection - it is a highly practical book, with immediate application for anyone who regularly uses data for arguments or presentations. We can't recommend this highly enough, so much so that we have two copies - one for lending out, and one for reference! Tufte's other books are also well worth exploring - 'Envisioning Information' (1990), 'Visual Explanations' (1997) and 'Beautiful Evidence' (2006). Tufte, E. 1988. 2nd Ed. Graphics Press.

Search

• Consumer Heterogeneity and Paid Search Effectiveness: A Large Scale Field Experiment: some fascinating research on the causal effectiveness of paid search advertisements at eBay. Their results suggest that, for eBay at least, “brand-keyword ads have no short-term benefits, and that returns from all other keywords are a fraction of conventional estimates”. A shot across Google's bows from the big brands. Blake, T. et al. 2013. National Bureau of Economic Research Working Paper (2013):1—26.
• Web Search: Multidisciplinary Perspectives: a rather unique collection of essays - scholars from a variety of disciplines consider web search engines (the entities) and web searching (the user behaviour). An invaluable resource for lecturers, researchers, students and (perhaps) practitioners in the fields of social sciences, communication studies, cultural studies, information science and, of course, search science. Section 1 covers social, cultural and philosophical perspectives; section 2 covers legal, political and economic perspectives; section 3 an information behaviour perspective. 2008 seems a long time ago now, but most of the perspectives are still highly relevant, and we found the non-technical perspectives tremendously helpful for our OfCom research project last year. Spink, A. & Zimmer, M. eds. 2008. Information Science and Knowledge Management vol. 14. Springer.
• PageRank and Beyond: the Science of Search Engine Rankings: a crash course in the history of Information Retrieval followed by a step-by-step guide to the mathematics of Google's PageRank algorithm. While it is aimed at people who have a handle on matrix maths (or, at least, used to and know where to go to look it up), and know their eigenvalues from their eigenvectors, it is actually fairly accessible and even entertaining -- rare in our experience for a Maths-heavy textbook. Inlcudes Matlab code for many algorithms, including HITS and PageRank. Langville, A. & Meyer, C. 2006. Princeton & Oxford.
• Search Engines & Ethics: a quick overview of the limited academic literature on the ethics of search engines. Gives a precis of some of the material in Web Search: Multidisciplinary Perspectives (see above), among other things. Very readable, avoiding philosophy jargon, and only uses one show-off German word (which it's quoting from another source). Tavani, H. 2012. Stanford.

Spam

• Safeguarding E-Commerce against Advisor Cheating Behaviors: Towards More Robust Trust Models for Handling Unfair Ratings: a great categorization of different types of review manipulation, with some suggestions for how to defend against them. Zhang, L. 2012. Final Year BEng Project, School of Computer Engineering, Nanyang Technological University.
• A Large-Scale Study of Link Spam Detection by Graph Algorithms: a study of the overall structure and distribution of link farms in a large-scale graph of the JapaneseWeb with 5.8 million sites and 283 million links. Shows an authority core, and a number of spam cores. An interesting approach. Saito et al. 2007. Proceedings of the 3rd international workshop on Adversarial information retrieval on the web, pp45—48.
• Transductive link Spam Detection: a take on using directed graphs to classify spam. Seemed to have some promising early results, but unclear how it has developed. Zhou, D et al. 2007. Proceedings of the 3rd international workshop on Adversarial information retrieval on the web.
• Link Spam Detection Based on Mass Estimation: explains the concept of spam mass, a measure of the impact of link spamming on a page's ranking. Gyöngyi, Z. et al. 2006. 32nd International Conference on Very Large Data Bases (VLDB 2006), Seoul, Korea.
• Web Spam Taxonomy: a comprehensive taxonomy of the spamming techniques current in 2005 – many of which are still in use today. It's by no means comprehensive, but an excellent place to start. Gyöngyi, Z & Garcia-Molina, H. 2005. Proceedings of the 1st International Workshop on Adversarial Information Retrieval on the Web.

Contact us

If there's anything you'd like to know more about in the realm of ecommerce + science,