Machine Learning and Grounded Theory Method
Published 4 November 2016
Michael Müller, Shion Guha, Eric P. S. Baumer, David Mimno, N. Sadat Shami
Citations81
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
New research directions are proposed that can further clarify the relationships between Grounded Theory Method and Machine Learning and that can use those relationships to strengthen the ability to describe the authors' phenomena and develop stronger hybrid theories.
Abstract
Grounded Theory Method (GTM) and Machine Learning (ML) are often considered to be quite different. In this note, we explore unexpected convergences between these methods. We propose new research directions that can further clarify the relationships between these methods, and that can use those relationships to strengthen our ability to describe our phenomena and develop stronger hybrid theories.
Keywords
Computer ScienceSocial Sciences
Sage eBooksBasics of qualitative research : techniques and procedures for developing grounded theory
38,901 Citations1998Anselm L. Strauss, Juliet Corbin
Contemporary Sociology A Journal of ReviewsBasics of Qualitative Research: Grounded Theory Procedures and Techniques.
29,422 Citations1992Carolyn Ellis, Anselm Strauss +1 more
Constructing grounded theory : a practical guide through qualitative analysis
18,755 Citations2006Kathy Charmaz
K Kathy Charmaz's excellent and practical guide to grounded theory in nursing and how to do qualitative research in nursing is welcomed.
Cambridge University Press eBooksQualitative Analysis for Social Scientists
11,756 Citations1987Anselm L. Strauss
This book presents a meta-coding pedagogical architecture grounded in awareness contexts that helps practitioners and students understand one another better and take responsibility for one another's learning.
Statistical Comparisons of Classifiers over Multiple Data Sets
11,198 Citations2006Janez Demšar
A set of simple, yet safe and robust non-parametric tests for statistical comparisons of classifiers is recommended: the Wilcoxon signed ranks test for comparison of two classifiers and the Friedman test with the corresponding post-hoc tests for comparisons of more classifiers over multiple data sets.
A study of cross-validation and bootstrap for accuracy estimation and model selection
10,733 Citations1995Ron Kohavi
The results indicate that for real-word datasets similar to the authors', the best method to use for model selection is ten fold stratified cross validation even if computation power allows using more folds.
Information Communication & SocietyCRITICAL QUESTIONS FOR BIG DATA
5,321 Citations2012danah boyd, Kate Crawford
Six provocations are offered to spark conversations about the issues of Big Data: a cultural, technological, and scholarly phenomenon that rests on the interplay of technology, analysis, and mythology that provokes extensive utopian and dystopian rhetoric.
TechnometricsPattern Recognition and Machine Learning
4,637 Citations2007Radford M. Neal
This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
Sociological TheoryTheory Construction in Qualitative Research
3,810 Citations2012Stefan Timmermans, Iddo Tavory
Information Systems ResearchStudying Information Technology in Organizations: Research Approaches and Assumptions
3,344 Citations1991Wanda J. Orlikowski, Jack J. Baroudi
It is suggested that much can be gained if a plurality of research perspectives is effectively employed to investigate information systems phenomena and that there exist other philosophical assumptions that can inform studies of the relationships between information technology, people, and organizations.
ScienceQuantitative Analysis of Culture Using Millions of Digitized Books
3,107 Citations2010Jean-Baptiste Michel, Yuan Shen +12 more
This work surveys the vast terrain of ‘culturomics,’ focusing on linguistic and cultural phenomena that were reflected in the English language between 1800 and 2000, and shows how this approach can provide insights about fields as diverse as lexicography, the evolution of grammar, collective memory, the adoption of technology and the pursuit of fame.
The SAGE Handbook of Grounded Theory
2,619 Citations2007Antony Bryant, Kathy Charmaz
Elsevier eBooksSupervised and Unsupervised Discretization of Continuous Features
1,931 Citations1995James Dougherty, Ron Kohavi +1 more
Binning, an unsupervised discretization method, is compared to entropy-based and purity-based methods, which are supervised algorithms, and it is found that the performance of the Naive-Bayes algorithm significantly improved when features were discretized using an entropy- based method.
Cheap and fast---but is it good?
1,906 Citations2008Rion Snow, Brendan O’Connor +2 more
This work explores the use of Amazon's Mechanical Turk system, a significantly cheaper and faster method for collecting annotations from a broad base of paid non-expert contributors over the Web, and proposes a technique for bias correction that significantly improves annotation quality on two tasks.
Remote Sensing of EnvironmentSelecting and interpreting measures of thematic classification accuracy
1,710 Citations1997Stephen V. Stehman
Characteristics of some commonly used accuracy measures are described, and relationships among these measures are provided to aid the user in choosing an appropriate measure.
Medical Entomology and ZoologyAwareness of Dying
1,314 Citations1965Barney G. Glaser, Anselm L. Strauss
Developing Grounded Theory : The Second Generation
929 Citations2018Janice M. Morse, Barbara J. Bowers +4 more
Journal of Machine Learning ResearchFeature Selection for Unsupervised Learning
890 Citations2004Jennifer Dy, Carla E. Brodley
This paper explores the feature selection problem and issues through FSSEM (Feature Subset Selection using Expectation-Maximization (EM) clustering) and through two different performance criteria for evaluating candidate feature subsets: scatter separability and maximum likelihood.
Journal of Machine Learning ResearchStatistical Comparisons of Classifiers over Multiple Data Sets
875 Citations2006DemšarJanez
Development and use of a gold-standard data set for subjectivity classifications
498 Citations1999Janyce Wiebe, Rebecca Bruce +1 more
Bias-corrected tags are formulated and successfully used to guide a revision of the coding manual and develop an automatic classifier.
Field MethodsIntercoder Reliability for Validating Conclusions Drawn from Open-Ended Interview Data
461 Citations2000Karen S. Kurasaki
A set of procedures was used to develop and assess intercoder reliability with free-flowing text data, in which the coders themselves determined the length of codable text segments, and suggest that these procedures may be useful for validating the conclusions drawn from other qualitative studies using text data.
Characterizing and predicting postpartum depression from shared facebook data
396 Citations2014Munmun De Choudhury, Scott Counts +2 more
It is found that increased social isolation and lowered availability of social capital on Facebook, are the best predictors of PPD in mothers.
American Behavioral ScientistDiscovery of Substantive Theory: A Basic Strategy Underlying Qualitative Research
388 Citations1965Barney G. Glaser, Anselm L. Strauss
Forum: Qualitative Social Research (Freie Universität Berlin)"Emergence" vs. "Forcing" of Empirical Data? A Crucial Problem of "Grounded Theory" Reconsidered
379 Citations2008Udo Kelle
interactionsInteractions with big data analytics
360 Citations2012Danyel Fisher, Rob DeLine +2 more
It is no surprise today that big data is useful for HCI researchers and user interface design, and A/B testing is a standard practice in the usability community to help determine relative differences in user performance using different interfaces.
Abduction: The Logic of Discovery of Grounded Theory
299 Citations2007Jo Reichertz
Echoes of power
277 Citations2012Cristian Danescu-Niculescu-Mizil, Lillian Lee +2 more
It is shown that in group discussions, power differentials between participants are subtly revealed by how much one individual immediately echoes the linguistic style of the person they are responding to, and an analysis framework based on linguistic coordination is proposed that works consistently across multiple types of power.
The language that gets people to give
253 Citations2014Tanushree Mitra, Éric Gilbert
The factors which lead to successfully funding a crowdfunding project are explored, and the language used in the project has surprising predictive power accounting for 58.56% of the variance around successful funding.
Journal of the Association for Information Science and TechnologyComparing grounded theory and topic modeling: Extreme divergence or unlikely convergence?
228 Citations2017Eric P. S. Baumer, David Mimno +3 more
This article describes the application of analysis methods from two distinct fields, one method from interpretive social science andOne method from statistical machine learning, to the same survey data, and suggests ways that such methods might be combined in novel and compelling ways.
The Media Frames Corpus: Annotations of Frames Across Issues
223 Citations2015Dallas Card, Amber E. Boydstun +3 more
The first version of the Media Frames Corpus is described: several thousand news articles on three policy issues, annotated in terms of media framing, motivating framing as a phenomenon of study for computational linguistics.
Computer Supported Cooperative Work (CSCW)Reflections on 25 Years of Ethnography in CSCW
184 Citations2013Jeanette Blomberg, Helena Karasti
It is argued that as the temporal and spatial horizons of inquiry have expanded, along with new domains of collaborative activity, ethnography continues to provide invaluable perspectives.
More than words
172 Citations2009Stephan Greene, Philip Resnik
A strong predictive connection between linguistically well motivated features and implicit sentiment is established, and it is shown how computational approximations of these features can be used to improve on existing state-of-the-art sentiment classification results.
Ways of Knowing in HCI
146 Citations2014Judith S. Olson, Wendy A. Kellogg
This textbook brings together both new and traditional research methods in Human Computer Interaction to gain an understanding of the type of knowledge each method provides, its disciplinary roots and how each contributes to understanding users, user behavior and the context of use.
The Heart Work of Wikipedia
103 Citations2015Amanda Menking, Ingrid Erickson
It is posited that the gendered and emotional labor required of many women to participate in Wikipedia's production renders it, problematically, a space of conflicting public and private spheres, motivated by antithetical open and closed values.
Understanding affect in the workplace via social media
100 Citations2013Munmun De Choudhury, Scott Counts
The landscape of affective expression of employees at a large Fortune 500 software corporation via an internal microblogging tool is investigated and it is found that positive affect is expressed through interpersonal communications that connect disparate geographic regions.
Curiosity, Creativity, and Surprise as Analytic Tools: Grounded Theory Method
100 Citations2014Michael Müller
Grounded Theory Method offers a rigorous way to explore a domain, with an emphasis on discovering new insights, testing those insights, and building partial understandings into a broader theory of the domain.
Testing and Comparing Computational Approaches for Identifying the Language of Framing in Political News
92 Citations2015Eric P. S. Baumer, Elisha Elovic +3 more
Results show that the best performing classifiers achieve performance comparable to that of human annotators, and they indicate which aspects of language most pertain to framing.
Social tagging roles
90 Citations2008Jennifer Thom-Santelli, Michael Müller +1 more
The concept of social roles are employed to describe audience-oriented tagging, including roles of community-seeker, community-builder, evangelist, publisher, and team-leader, to contribute to the understanding of the motivations and rationales behind social tagging in an international company.
Directory of Open access Books (OAPEN Foundation)Computer Vision Metrics: Survey, Taxonomy, and Analysis
83 Citations2014Scott Krig
Social Media + SocietyMissing Photos, Suffering Withdrawal, or Finding Freedom? How Experiences of Social Media Non-Use Influence the Likelihood of Reversion
75 Citations2015Eric P. S. Baumer, Shion Guha +3 more
CUNY Academic Works (City University of New York)Topic Modeling and Figurative Language
62 Citations2012Lisa Marie Rhody
Turkers, Scholars, "Arafat" and "Peace"
45 Citations2015Shilad Sen, Margaret E. Giesel +7 more
It is shown that crowdworkers on Mechanical Turk produce significantly different semantic relatedness gold standard judgements than people from other communities, which problematize the notion that a universal gold standard dataset exists for all knowledge tasks.
OPAL (Open@LaTrobe) (La Trobe University)Self-Organizing Agile Teams: A Grounded Theory
35 Citations2011Rashina Hoda
International Conference on Program ComprehensionLicense usage and changes: a large-scale study of Java projects on GitHub
22 Citations2015Christopher Vendome, Mario Linares‐Vásquez +4 more
interactionsData in the wild
21 Citations2013Chee Siang Ang, Ania Bobrowicz +2 more
Data-mining techniques to search for emerging patterns in existing datasets—rather than generate new data for planned hypothesis testing or qualitative exploration—is transforming the way research is being conducted, with a loss of philosophical and epistemological grounding.
AI MagazineA Machine‐Learning Approach to the Detection of Fetal Hypoxia during Labor and Delivery
18 Citations2012Philip Warrick, Emily Hamilton +2 more
This article presents a novel approach to hypoxia detection based on recordings of the uterine pressure and fetal heart rate, which are obtained using standard labor monitoring devices and uses a unique database of real clinical recordings, both from normal and pathological cases.
Characterizing Example Embedding as a software activity
14 Citations2009Ohad Barzilay, Orit Hazzan +1 more
An empirical qualitative software engineering research is used to characterize Example Embedding as a software activity - a collection of fine grained techniques which together assemble an abstract key notion in software development.
Realising web effort estimation
8 Citations2013Olavo Olimpio Matos, Luiz Leandro Fortaleza +2 more
This paper employs qualitative research with the participation of four different Web development companies in Manaus (Brazil) using semi-structured interviews for data collection and uses Grounded Theory-based procedures to identify and combine factors affecting the estimation of Web projects.
DOAJ (DOAJ: Directory of Open Access Journals)Opportunizing: A classic grounded theory study on business and management
6 Citations2006Ólavur Christiansen
coDNA
2 Citations2015Ofer Arazy, Henry Brausen +4 more
The coDNA visualization tool -- coDNA -- supports researchers in the development of grounded theory of peer production and allows practitioners to monitor production processes within their online community.