Author: David Carmel
Publisher: Springer Nature
ISBN: 3031022726
Category : Computers
Languages : en
Pages : 77
Book Description
Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify "difficult" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty. Table of Contents: Introduction - The Robustness Problem of Information Retrieval / Basic Concepts / Query Performance Prediction Methods / Pre-Retrieval Prediction Methods / Post-Retrieval Prediction Methods / Combining Predictors / A General Model for Query Difficulty / Applications of Query Difficulty Estimation / Summary and Conclusions
Estimating the Query Difficulty for Information Retrieval
Author: David Carmel
Publisher: Springer Nature
ISBN: 3031022726
Category : Computers
Languages : en
Pages : 77
Book Description
Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify "difficult" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty. Table of Contents: Introduction - The Robustness Problem of Information Retrieval / Basic Concepts / Query Performance Prediction Methods / Pre-Retrieval Prediction Methods / Post-Retrieval Prediction Methods / Combining Predictors / A General Model for Query Difficulty / Applications of Query Difficulty Estimation / Summary and Conclusions
Publisher: Springer Nature
ISBN: 3031022726
Category : Computers
Languages : en
Pages : 77
Book Description
Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify "difficult" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty. Table of Contents: Introduction - The Robustness Problem of Information Retrieval / Basic Concepts / Query Performance Prediction Methods / Pre-Retrieval Prediction Methods / Post-Retrieval Prediction Methods / Combining Predictors / A General Model for Query Difficulty / Applications of Query Difficulty Estimation / Summary and Conclusions
Estimating the Query Difficulty for Information Retrieval
Author: David Carmel
Publisher: Morgan & Claypool Publishers
ISBN: 160845357X
Category : Computers
Languages : en
Pages : 77
Book Description
Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify "difficult" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty. Table of Contents: Introduction - The Robustness Problem of Information Retrieval / Basic Concepts / Query Performance Prediction Methods / Pre-Retrieval Prediction Methods / Post-Retrieval Prediction Methods / Combining Predictors / A General Model for Query Difficulty / Applications of Query Difficulty Estimation / Summary and Conclusions
Publisher: Morgan & Claypool Publishers
ISBN: 160845357X
Category : Computers
Languages : en
Pages : 77
Book Description
Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify "difficult" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty. Table of Contents: Introduction - The Robustness Problem of Information Retrieval / Basic Concepts / Query Performance Prediction Methods / Pre-Retrieval Prediction Methods / Post-Retrieval Prediction Methods / Combining Predictors / A General Model for Query Difficulty / Applications of Query Difficulty Estimation / Summary and Conclusions
Introduction to Information Retrieval
Author: Christopher D. Manning
Publisher: Cambridge University Press
ISBN: 1139472100
Category : Computers
Languages : en
Pages :
Book Description
Class-tested and coherent, this textbook teaches classical and web information retrieval, including web search and the related areas of text classification and text clustering from basic concepts. It gives an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections. All the important ideas are explained using examples and figures, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science. Based on feedback from extensive classroom experience, the book has been carefully structured in order to make teaching more natural and effective. Slides and additional exercises (with solutions for lecturers) are also available through the book's supporting website to help course instructors prepare their lectures.
Publisher: Cambridge University Press
ISBN: 1139472100
Category : Computers
Languages : en
Pages :
Book Description
Class-tested and coherent, this textbook teaches classical and web information retrieval, including web search and the related areas of text classification and text clustering from basic concepts. It gives an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections. All the important ideas are explained using examples and figures, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science. Based on feedback from extensive classroom experience, the book has been carefully structured in order to make teaching more natural and effective. Slides and additional exercises (with solutions for lecturers) are also available through the book's supporting website to help course instructors prepare their lectures.
Mobile Search Behaviors
Author: Dan Wu
Publisher: Springer Nature
ISBN: 3031023153
Category : Computers
Languages : en
Pages : 159
Book Description
With the rapid development of mobile Internet and smart personal devices in recent years, mobile search has gradually emerged as a key method with which users seek online information. In addition, cross-device search also has been regarded recently as an important research topic. As more mobile applications (APPs) integrate search functions, a user's mobile search behavior on different APPs becomes more significant. This book provides a systematic review of current mobile search analysis and studies user mobile search behavior from several perspectives, including mobile search context, APP usage, and different devices. Two different user experiments to collect user behavior data were conducted. Then, through the data from user mobile phone usage logs in natural settings, we analyze the mobile search strategies employed and offer a context-based mobile search task collection, which then can be used to evaluate the mobile search engine. In addition, we combine mobile search with APP usage to give more in-depth analysis, such as APP transition in mobile search and follow-up actions triggered by mobile search. The study, combining the mobile search with APP usage, can contribute to the interaction design of APPs, such as the search recommendation and APP recommendation. Addressing the phenomenon of users owning more smart devices today than ever before, we focus on user cross device search behavior. We model the information preparation behavior and information resumption behavior in cross-device search and evaluate the search performance in cross-device search. Research on mobile search behaviors across different devices can help to understand online user information behavior comprehensively and help users resume their search tasks on different devices.
Publisher: Springer Nature
ISBN: 3031023153
Category : Computers
Languages : en
Pages : 159
Book Description
With the rapid development of mobile Internet and smart personal devices in recent years, mobile search has gradually emerged as a key method with which users seek online information. In addition, cross-device search also has been regarded recently as an important research topic. As more mobile applications (APPs) integrate search functions, a user's mobile search behavior on different APPs becomes more significant. This book provides a systematic review of current mobile search analysis and studies user mobile search behavior from several perspectives, including mobile search context, APP usage, and different devices. Two different user experiments to collect user behavior data were conducted. Then, through the data from user mobile phone usage logs in natural settings, we analyze the mobile search strategies employed and offer a context-based mobile search task collection, which then can be used to evaluate the mobile search engine. In addition, we combine mobile search with APP usage to give more in-depth analysis, such as APP transition in mobile search and follow-up actions triggered by mobile search. The study, combining the mobile search with APP usage, can contribute to the interaction design of APPs, such as the search recommendation and APP recommendation. Addressing the phenomenon of users owning more smart devices today than ever before, we focus on user cross device search behavior. We model the information preparation behavior and information resumption behavior in cross-device search and evaluate the search performance in cross-device search. Research on mobile search behaviors across different devices can help to understand online user information behavior comprehensively and help users resume their search tasks on different devices.
Web Indicators for Research Evaluation
Author: Michael Thelwall
Publisher: Springer Nature
ISBN: 3031023048
Category : Computers
Languages : en
Pages : 155
Book Description
In recent years there has been an increasing demand for research evaluation within universities and other research-based organisations. In parallel, there has been an increasing recognition that traditional citation-based indicators are not able to reflect the societal impacts of research and are slow to appear. This has led to the creation of new indicators for different types of research impact as well as timelier indicators, mainly derived from the Web. These indicators have been called altmetrics, webometrics or just web metrics. This book describes and evaluates a range of web indicators for aspects of societal or scholarly impact, discusses the theory and practice of using and evaluating web indicators for research assessment and outlines practical strategies for obtaining many web indicators. In addition to describing impact indicators for traditional scholarly outputs, such as journal articles and monographs, it also covers indicators for videos, datasets, software and other non-standard scholarly outputs. The book describes strategies to analyse web indicators for individual publications as well as to compare the impacts of groups of publications. The practical part of the book includes descriptions of how to use the free software Webometric Analyst to gather and analyse web data. This book is written for information science undergraduate and Master’s students that are learning about alternative indicators or scientometrics as well as Ph.D. students and other researchers and practitioners using indicators to help assess research impact or to study scholarly communication.
Publisher: Springer Nature
ISBN: 3031023048
Category : Computers
Languages : en
Pages : 155
Book Description
In recent years there has been an increasing demand for research evaluation within universities and other research-based organisations. In parallel, there has been an increasing recognition that traditional citation-based indicators are not able to reflect the societal impacts of research and are slow to appear. This has led to the creation of new indicators for different types of research impact as well as timelier indicators, mainly derived from the Web. These indicators have been called altmetrics, webometrics or just web metrics. This book describes and evaluates a range of web indicators for aspects of societal or scholarly impact, discusses the theory and practice of using and evaluating web indicators for research assessment and outlines practical strategies for obtaining many web indicators. In addition to describing impact indicators for traditional scholarly outputs, such as journal articles and monographs, it also covers indicators for videos, datasets, software and other non-standard scholarly outputs. The book describes strategies to analyse web indicators for individual publications as well as to compare the impacts of groups of publications. The practical part of the book includes descriptions of how to use the free software Webometric Analyst to gather and analyse web data. This book is written for information science undergraduate and Master’s students that are learning about alternative indicators or scientometrics as well as Ph.D. students and other researchers and practitioners using indicators to help assess research impact or to study scholarly communication.
Interactive IR User Study Design, Evaluation, and Reporting
Author: Jiqun Liu
Publisher: Springer Nature
ISBN: 3031023196
Category : Computers
Languages : en
Pages : 75
Book Description
Since user study design has been widely applied in search interactions and information retrieval (IR) systems evaluation studies, a deep reflection and meta-evaluation of interactive IR (IIR) user studies is critical for sharpening the instruments of IIR research and improving the reliability and validity of the conclusions drawn from IIR user studies. To this end, we developed a faceted framework for supporting user study design, reporting, and evaluation based on a systematic review of the state-of-the-art IIR research papers recently published in several top IR venues (n=462). Within the framework, we identify three major types of research focuses, extract and summarize facet values from specific cases, and highlight the under-reported user study components which may significantly affect the results of research. Then, we employ the faceted framework in evaluating a series of IIR user studies against their respective research questions and explain the roles and impacts of the underlying connections and "collaborations" among different facet values. Through bridging diverse combinations of facet values with the study design decisions made for addressing research problems, the faceted framework can shed light on IIR user study design, reporting, and evaluation practices and help students and young researchers design and assess their own studies.
Publisher: Springer Nature
ISBN: 3031023196
Category : Computers
Languages : en
Pages : 75
Book Description
Since user study design has been widely applied in search interactions and information retrieval (IR) systems evaluation studies, a deep reflection and meta-evaluation of interactive IR (IIR) user studies is critical for sharpening the instruments of IIR research and improving the reliability and validity of the conclusions drawn from IIR user studies. To this end, we developed a faceted framework for supporting user study design, reporting, and evaluation based on a systematic review of the state-of-the-art IIR research papers recently published in several top IR venues (n=462). Within the framework, we identify three major types of research focuses, extract and summarize facet values from specific cases, and highlight the under-reported user study components which may significantly affect the results of research. Then, we employ the faceted framework in evaluating a series of IIR user studies against their respective research questions and explain the roles and impacts of the underlying connections and "collaborations" among different facet values. Through bridging diverse combinations of facet values with the study design decisions made for addressing research problems, the faceted framework can shed light on IIR user study design, reporting, and evaluation practices and help students and young researchers design and assess their own studies.
Images in Social Media
Author: Susanne Ørnager
Publisher: Springer Nature
ISBN: 3031023145
Category : Computers
Languages : en
Pages : 101
Book Description
This book focuses on the methodologies, organization, and communication of digital image collection research that utilizes social media content. ("Image" is here understood as a cultural, conventional, and commercial—stock photo—representation.) The lecture offers expert views that provide different interpretations of images and their potential implementations. Linguistic and semiotic methodologies as well as eye-tracking research are employed to both analyze images and comprehend how humans consider them, including which salient features generally attract viewers' attention. This literature review covers image—specifically photographic—research since 2005, when major social media platforms emerged. A citation analysis includes an overview of co-citation maps that demonstrate the nexus of image research literature and the journals in which they appear. Eye tracking tests whether scholarly templates focus on the proper features of an image, such as people, objects, time, etc., and if a prescribed theme affects the eye movements of the observer. The results may point to renewed requirements for building image search engines. As it stands, image management already requires new algorithms and a new understanding that involves text recognition and very large database processing. The aim of this book is to present different image research areas and demonstrate the challenges image research faces. The book's scope is, by necessity, far from comprehensive, since the field of digital image research does not cover fake news, image manipulation, mobile photos, etc.; these issues are very complex and need a publication of their own. This book should primarily be useful for students in library and information science, psychology, and computer science.
Publisher: Springer Nature
ISBN: 3031023145
Category : Computers
Languages : en
Pages : 101
Book Description
This book focuses on the methodologies, organization, and communication of digital image collection research that utilizes social media content. ("Image" is here understood as a cultural, conventional, and commercial—stock photo—representation.) The lecture offers expert views that provide different interpretations of images and their potential implementations. Linguistic and semiotic methodologies as well as eye-tracking research are employed to both analyze images and comprehend how humans consider them, including which salient features generally attract viewers' attention. This literature review covers image—specifically photographic—research since 2005, when major social media platforms emerged. A citation analysis includes an overview of co-citation maps that demonstrate the nexus of image research literature and the journals in which they appear. Eye tracking tests whether scholarly templates focus on the proper features of an image, such as people, objects, time, etc., and if a prescribed theme affects the eye movements of the observer. The results may point to renewed requirements for building image search engines. As it stands, image management already requires new algorithms and a new understanding that involves text recognition and very large database processing. The aim of this book is to present different image research areas and demonstrate the challenges image research faces. The book's scope is, by necessity, far from comprehensive, since the field of digital image research does not cover fake news, image manipulation, mobile photos, etc.; these issues are very complex and need a publication of their own. This book should primarily be useful for students in library and information science, psychology, and computer science.
Trustworthy Policies for Distributed Repositories
Author: Reagan W. Moore
Publisher: Springer Nature
ISBN: 303102303X
Category : Computers
Languages : en
Pages : 133
Book Description
A trustworthy repository provides assurance in the form of management documents, event logs, and audit trails that digital objects are being managed correctly. The assurance includes plans for the sustainability of the repository, the accession of digital records, the management of technology evolution, and the mitigation of the risk of data loss. A detailed assessment is provided by the ISO-16363:2012 standard, "Space data and information transfer systems—Audit and certification of trustworthy digital repositories." This book examines whether the ISO specification for trustworthiness can be enforced by computer actionable policies. An implementation of the policies is provided and the policies are sorted into categories for procedures to manage externally generated documents, specify repository parameters, specify preservation metadata attributes, specify audit mechanisms for all preservation actions, specify control of preservation operations, and control preservation properties as technology evolves. An application of the resulting procedures is made to enforce trustworthiness within National Science Foundation data management plans.
Publisher: Springer Nature
ISBN: 303102303X
Category : Computers
Languages : en
Pages : 133
Book Description
A trustworthy repository provides assurance in the form of management documents, event logs, and audit trails that digital objects are being managed correctly. The assurance includes plans for the sustainability of the repository, the accession of digital records, the management of technology evolution, and the mitigation of the risk of data loss. A detailed assessment is provided by the ISO-16363:2012 standard, "Space data and information transfer systems—Audit and certification of trustworthy digital repositories." This book examines whether the ISO specification for trustworthiness can be enforced by computer actionable policies. An implementation of the policies is provided and the policies are sorted into categories for procedures to manage externally generated documents, specify repository parameters, specify preservation metadata attributes, specify audit mechanisms for all preservation actions, specify control of preservation operations, and control preservation properties as technology evolves. An application of the resulting procedures is made to enforce trustworthiness within National Science Foundation data management plans.
Framing Privacy in Digital Collections with Ethical Decision Making
Author: Virginia Dressler
Publisher: Springer Nature
ISBN: 3031023161
Category : Computers
Languages : en
Pages : 85
Book Description
As digital collections continue to grow, the underlying technologies to serve up content also continue to expand and develop. As such, new challenges are presented which continue to test ethical ideologies in everyday environs of the practitioner. There are currently no solid guidelines or overarching codes of ethics to address such issues. The digitization of modern archival collections, in particular, presents interesting conundrums when factors of privacy are weighed and reviewed in both small and mass digitization initiatives. Ethical decision making needs to be present at the onset of project planning in digital projects of all sizes, and we also need to identify the role and responsibility of the practitioner to make more virtuous decisions on behalf of those with no voice or awareness of potential privacy breaches. In this book, notions of what constitutes private information are discussed, as is the potential presence of such information in both analog and digital collections. This book lays groundwork to introduce the topic of privacy within digital collections by providing some examples from documented real-world scenarios and making recommendations for future research. A discussion of the notion privacy as concept will be included, as well as some historical perspective (with perhaps one the most cited work on this topic, for example, Warren and Brandeis' "Right to Privacy," 1890). Concepts from the The Right to Be Forgotten case in 2014 (Google Spain SL, Google Inc. v Agencia Españla de Protección de Datos, Mario Costeja González) are discussed as to how some lessons may be drawn from the response in Europe and also how European data privacy laws have been applied. The European ideologies are contrasted with the Right to Free Speech in the First Amendment in the U.S., highlighting the complexities in setting guidelines and practices revolving around privacy issues when applied to real life scenarios. Two ethical theories are explored: Consequentialism and Deontological. Finally, ethical decision making models will also be applied to our framework of digital collections. Three case studies are presented to illustrate how privacy can be defined within digital collections in some real-world examples.
Publisher: Springer Nature
ISBN: 3031023161
Category : Computers
Languages : en
Pages : 85
Book Description
As digital collections continue to grow, the underlying technologies to serve up content also continue to expand and develop. As such, new challenges are presented which continue to test ethical ideologies in everyday environs of the practitioner. There are currently no solid guidelines or overarching codes of ethics to address such issues. The digitization of modern archival collections, in particular, presents interesting conundrums when factors of privacy are weighed and reviewed in both small and mass digitization initiatives. Ethical decision making needs to be present at the onset of project planning in digital projects of all sizes, and we also need to identify the role and responsibility of the practitioner to make more virtuous decisions on behalf of those with no voice or awareness of potential privacy breaches. In this book, notions of what constitutes private information are discussed, as is the potential presence of such information in both analog and digital collections. This book lays groundwork to introduce the topic of privacy within digital collections by providing some examples from documented real-world scenarios and making recommendations for future research. A discussion of the notion privacy as concept will be included, as well as some historical perspective (with perhaps one the most cited work on this topic, for example, Warren and Brandeis' "Right to Privacy," 1890). Concepts from the The Right to Be Forgotten case in 2014 (Google Spain SL, Google Inc. v Agencia Españla de Protección de Datos, Mario Costeja González) are discussed as to how some lessons may be drawn from the response in Europe and also how European data privacy laws have been applied. The European ideologies are contrasted with the Right to Free Speech in the First Amendment in the U.S., highlighting the complexities in setting guidelines and practices revolving around privacy issues when applied to real life scenarios. Two ethical theories are explored: Consequentialism and Deontological. Finally, ethical decision making models will also be applied to our framework of digital collections. Three case studies are presented to illustrate how privacy can be defined within digital collections in some real-world examples.
Video Structure Meaning
Author: Brian C O'Connor
Publisher: Springer Nature
ISBN: 303102320X
Category : Computers
Languages : en
Pages : 79
Book Description
For over a century, motion pictures have entertained us, occasionally educated us, and even served a few specialized fields of study. Now, however, with the precipitous drop in prices and increase in image quality, motion pictures are as widespread as paperback books and postcards once were. Yet, theories and practices of analysis for particular genres and analytical stances, definitions, concepts, and tools that span platforms have been wanting. Therefore, we developed a suite of tools to enable close structural analysis of the time-varying signal set of a movie. We take an information-theoretic approach (message is a signal set) generated (coded) under various antecedents (sent over some channel) decoded under some other set of antecedents. Cultural, technical, and personal antecedents might favor certain message-making systems over others. The same holds true at the recipient end-yet, the signal set remains the signal set. In order to discover how movies work-their structure and meaning-we honed ways to provide pixel level analysis, forms of clustering, and precise descriptions of what parts of a signal influence viewer behavior. We assert that analysis of the signal set across the evolution of film—from Edison to Hollywood to Brakhage to cats on social media—yields a common ontology with instantiations (responses to changes in coding and decoding antecedents).
Publisher: Springer Nature
ISBN: 303102320X
Category : Computers
Languages : en
Pages : 79
Book Description
For over a century, motion pictures have entertained us, occasionally educated us, and even served a few specialized fields of study. Now, however, with the precipitous drop in prices and increase in image quality, motion pictures are as widespread as paperback books and postcards once were. Yet, theories and practices of analysis for particular genres and analytical stances, definitions, concepts, and tools that span platforms have been wanting. Therefore, we developed a suite of tools to enable close structural analysis of the time-varying signal set of a movie. We take an information-theoretic approach (message is a signal set) generated (coded) under various antecedents (sent over some channel) decoded under some other set of antecedents. Cultural, technical, and personal antecedents might favor certain message-making systems over others. The same holds true at the recipient end-yet, the signal set remains the signal set. In order to discover how movies work-their structure and meaning-we honed ways to provide pixel level analysis, forms of clustering, and precise descriptions of what parts of a signal influence viewer behavior. We assert that analysis of the signal set across the evolution of film—from Edison to Hollywood to Brakhage to cats on social media—yields a common ontology with instantiations (responses to changes in coding and decoding antecedents).