Most of us have gone online to search for information about health. What are the symptoms of a migraine? How effective is this drug? Where can I find more resources for cancer patients? Could I have an STD? Am I fat? A Pew survey reports more than 80 percent of American Internet users have logged on to ask questions like these. But what if the digital traces left by our searches could show doctors and medical researchers something new and interesting? What if the data generated by our searches could reveal information about health that would be difficult to gather in other ways? In this book, Elad Yom-Tov argues that Internet data could change the way medical research is done, supplementing traditional tools to provide insights not otherwise available. He describes how studies of Internet searches have, among other things, already helped researchers track to side effects of prescription drugs, to understand the information needs of cancer patients and their families, and to recognize some of the causes of anorexia.
Yom-Tov shows that the information collected can benefit humanity without sacrificing individual privacy. He explains why people go to the Internet with health questions; for one thing, it seems to be a safe place to ask anonymously about such matters as obesity, sex, and pregnancy. He describes in detrimental effects of “pro-anorexia” online content; tells how computer scientists can scour search engine data to improve public health by, for example, identifying risk factors for disease and centers of contagion; and tells how analyses of how people deal with upsetting diagnoses help doctors to treat patients and patients to understand their conditions.
Table of Contents: Evolution of Multimedia Information Systems: 1990-2008 / Survey of Automatic Metadata Creation Methods / Refinement of Automatic Metadata / Multimedia Surrogates / End-User Utility for Metadata and Surrogates: Effectiveness, Efficiency, and Satisfaction
Table of Contents: Introduction / Web Impact Assessment / Link Analysis / Blog Searching / Automatic Search Engine Searches: LexiURL Searcher / Web Crawling: SocSciBot / Search Engines and Data Reliability / Tracking User Actions Online / Advaned Techniques / Summary and Future Directions
In this book we provide a comprehensive and up-to-date introduction to Dynamic Information Retrieval Modeling, the statistical modeling of IR systems that can adapt to change. We define dynamics, what it means within the context of IR and highlight examples of problems where dynamics play an important role. We cover techniques ranging from classic relevance feedback to the latest applications of partially observable Markov decision processes (POMDPs) and a handful of useful algorithms and tools for solving IR problems incorporating dynamics.
The theoretical component is based around the Markov Decision Process (MDP), a mathematical framework taken from the field of Artificial Intelligence (AI) that enables us to construct models that change according to sequential inputs. We define the framework and the algorithms commonly used to optimize over it and generalize it to the case where the inputs aren't reliable. We explore the topic of reinforcement learning more broadly and introduce another tool known as a Multi-Armed Bandit which is useful for cases where exploring model parameters is beneficial. Following this we introduce theories and algorithms which can be used to incorporate dynamics into an IR model before presenting an array of state-of-the-art research that already does, such as in the areas of session search and online advertising.
Change is at the heart of modern Information Retrieval systems and this book will help equip the reader with the tools and knowledge needed to understand Dynamic Information Retrieval Modeling.