TheHandbook of Latent Semantic Analysisis the authoritative reference for the theory behind Latent Semantic Analysis (LSA), a burgeoning mathematical method used to analyze how words make meaning, with the desired outcome to program machines to understand human commands via natural language rather than strict programming protocols. The first book of its kind to deliver such a comprehensive analysis, this volume explores every area of the method and combines theoretical implications as well as practical matters of LSA. Readers will be introduced to a powerful new way of understanding language phenomena, as well as innovative ways to perform tasks that depend on language or other complex systems. TheHandbookclarifies misunderstandings and pre-formed objections to LSA, and provides examples of exciting new educational technologies made possible by LSA and similar techniques. It raises issues in philosophy, artificial intelligence, and linguistics, while describing how LSA has underwritten a range of educational technologies and information systems. Alternate approaches to language understanding are addressed and compared to LSA. This workis essential reading for anyonenewcomers to this area and experts alikeinterested in how human language works or interested in computational analysis and uses of text. Educational technologists, cognitive scientists, philosophers, and information technologists in particular will consider this volume especially useful.

Tom Landauer is a theoretical and applied cognitive scientist, with interests on the one hand in advancing understanding of how complex knowledge, such as language, is learned and used, and on the other hand in creating instructional methods and automated aids to speed and enhance knowledge acquisition and use. He led the brilliant team of young cognitive scientists at Bell Communications Research that invented LSA and, along with Susan Dumais, pioneered LSA’s interpretation and validation as a theory of verbal meaning. He is currently a Research Professor at the University of Colorado, Boulder, and Executive Vice President at Pearson Knowledge Technologies, a subsidiary of Pearson, the international educational publishing and assessment company. A 1960 Harvard Ph.D., he served on faculties of The Harvard Graduate School of education, Dartmouth College, and Stanford University, and was a Visiting Lecturer at Princeton University. From 1969-1984, he was a researcher and research director at Bell Telephone Laboratories and its successor, Bell Communications Research. Tom is a devoted proponent of the “Pasteur’s Quadrant” scientific method: taking problems from practical needs, finding solutions by empirical research and rigorous modeling, and testing theories and solutions by their effectiveness and completeness in solving the inspiring practical problem. (For example, LSA provides a rigorous theory of verbal meaning with wide applicability, but is unable to explain syntactic phenomena.) His research has almost always centered on some aspect of learning, from its physiology and biochemistry to the effects of practice schedules to mathematical theories, and to applications as diverse as marketing, children’s social development, human-computer interaction, and the specification of memorable telephone numbers. He regards LSA as by far the most significant accomplishment with which he has been associated. 
Danielle S. McNamara is a cognitive scientist in the Department of Psychology at the University of Memphis. A great deal of her work involves the theoretical study of cognition as well as the application of cognition to educational practice. She examines a variety of phenomena related to reading, comprehension skill, working memory, communication, expertise, knowledge acquisition, and the generation effect. A major thrust of her research concerns how to improve comprehension and learning from text. One focus of that research is on providing training to improve metacognitive reading strategies. For example, she and her research team developed an automated reading strategy tutor called ISTART (Interactive Strategy Trainer for Active Reading and Thinking) that teaches readers to more effectively understand difficult text. A second focus of her reading research is on text cohesion and how that interacts with reader aptitudes. She and her research team have developed Coh-Metrix, an automated tool that assesses text on multiple dimensions, including text cohesion. Many of her projects, such as the iSTART and Coh-Metrix projects, involve the creation and refinement of computational algorithms to extract meaning from text and to automatically interpret and respond to text and discourse. LSA has played an important role in these endeavors. 
Simon Dennis is a psychologist and computer scientist with interests in human memory and language processes. His work on recognition memory has precipitated a fundamental rethink about the sources of interference in episodic memory paradigms, while his Syntagmatic Paradigmatic model has provided a solution to the question of how people abstract thematic role information from text as well as providing insight into the nature of inference in text comprehension. He completed his training at the University of Queensland before becoming a lecturer in the Australian Research Council's, Key Centre for Human Factors and Applied Cognitive Psychology. He then moved to United States to take on the role of Research Professor at the University of Colorado at Boulder. He currently holds a lectureship in the School of Psychology at the University of Adelaide, Australia.
Walter Kintsch is Professor Emeritus in the Department of Psychology at the University of Colorado and the former director of its Institute of Cognitive Science. His research has focused on the psychology of language, in particular models of discourse comprehension. This work is summarized in his book Comprehension: A Paradigm for Cognition. In recent years he has explored the use of LSA both as a tool for theorizing about language comprehension and for comprehension instruction in schools. A software called Summary Street that provides content feedback to middle school students writing summaries has been introduced and successfully tested in a large number of schools in Colorado. His current interests include the exploration of how the semantic information that is stored in long-term memory by LSA-like models is used to construct the full, contextually appropriate meaning of a word in working memory when the word is used as part of a discourse.