Collective intelligence applied to legal e-discovery: A ten-year case study of Australia franchise and trademark litigation
Introduction
This research focuses on developing a methodology for legal e-discovery and, most importantly, litigation evolution analysis using collective intelligence of precedential documents, court cases, and data existing in legal databases. The specific techniques of text mining, data mining, cluster analysis, and formal concept analysis are modified and applied as the Collective Litigation Intelligence (CLI) methodology for legal e-discovery. The case study of the Australia retail franchise and trademark litigation is used to demonstrate the effectiveness of the generalizable CLI processes. The last decade of legal cases (2004–2013), related to retail franchises and trademarks, are searched as the fact-base to derive collective litigation intelligence to project the litigation trends and evaluate hazards underlying the retail legal evolution. These franchise and trademark litigation cases and selected documents are used to demonstrate the significant findings of the CLI approach and the validity of the methodology. The paper strategically advises franchise trademark holders of market strategies for sustainable market development that avoids past mistakes and identifies new opportunities. The research results enables managers and legal advisors to answer critical questions such as “Has legislation stabilized the franchise environment?” and “What are the trademark, legal, and franchise hazards that restrict market development?” The research clusters the last decade of 35 precedent setting franchise and trademark cases into four homogenous groups. Briefly speaking, the clustering analysis yields four groups of cases with distinctive characteristics and features. The CLI’s final step is to derive the time-varied evolution trends underlying the development of the franchise and trademark legal landscape. Applying the developed CLI processes, Clusters 1, 2, and 3 are considered bellwether case clusters whereas Cluster 4 supports legislative stability and a market place of opportunity rather than a legal hazard. Franchisers and brand managers interested in the Australian market should focus on the case clusters to avoid franchise and trademark litigation and to develop opportunities that create sustainable market plans. The methodology and the case research can be rapidly repeated in other legal domains for their litigation e-discovery.
This paper is organized using the following sections. In the literature review section, the key concepts and related research of ontology, knowledge discovery, data and text mining, and formal concept analysis are reviewed, cited, and described. We refer to these papers for the readers’ further reference and study when conducting following up research for advanced theory development and applications. The “collective litigation intelligence (CLI) methodology” section describes the CLI methodology framework and logic for each detailed step. The CLI procedure is best demonstrated and described using an applied legal case study. Thus, the step-wise sub-sections including the document search strategy, the case text mining, the CLI clustering and context interpretations, and legal concept evolution lattice are presented using the Australian franchise example. Finally, the conclusion section discusses the research results, contributions, and suggested future work for a generalizable CLI methodology applicable for legal e-discovery beyond the franchise and trademark case domain.
Section snippets
Literature review
This research focuses on using knowledge discovery algorithms and methods to effectively extract litigation trends and insights from a huge collection of text documents. The key knowledge e-discovery techniques specifically applicable for CLI methodology development include the capturing of key entities in the domain ontology, knowledge discovery from text documents (KDT) and from databases (KDD), document clustering, and formal concept lattice analysis. From these critical components of
Collective litigation intelligence (CLI) methodology
This research develops the formal methodology for the discovery of collective litigation intelligence. The main processes to the CLI approach are illustrated in Fig. 3, which include the litigation case search strategy and execution, the legal document text mining, the case clustering, and the CLI concept evolution lattice analysis. As shown in Fig. 4, the CLI processes are implemented for the Australia retail franchise and trademark related litigation activities and trend analysis. The
Discussion and conclusions
This research develops a generalizable Collective Litigation Intelligence (CLI) e-discovery methodology and demonstrates the approach in practice using the case study of Australia’s franchise and trademark litigation cases. The results of CLI e-discovery for the case study show that Australia has a well regulated retail marketplace with solid legislation to support franchises and protect trademarks. There are three important points derived from this research to be considered when entering the
Acknowledgement
This research was partially supported by research grants (NSC 102-2410-H-009-053-MY3, NSC 103-2218-E-007-007) funded by the Ministry of Science and Technology. The authors appreciate the discussions with Professor Kamal Puri, the Faculty of Law at Queensland University of Technology, which helped the legal foundation of this research.
References (27)
- et al.
Monitoring trends of technological changes based on the dynamic patent lattice. A modified formal concept analysis approach
Technol. Forecast. Soc. Change
(2011) - et al.
Term-weighting approaches in automatic text retrieval
Inform. Process. Manage.
(1988) - et al.
Text mining techniques for patent analysis
Inform. Process. Manage.
(2007) Lattice Theory
(1973)- et al.
Data Mining Techniques: for Marketing, Sales, and Customer Support
(1997) - Copyright Act (Cth), Australia...
Exploiting franchisee vulnerability
Franchise Law Colloquium
(2008)Knowledge discovery and data mining in databases
Handbook Software Eng. Knowledge Eng.
(2001)- et al.
From data mining to knowledge discovery in databases
AI Magazine
(1996) - et al.
Knowledge discovery in textual databases (KDT)
Knowledge discovery in databases: an overview
AI Magazine
Ontologies and knowledge bases, towards a terminological clarification
Technology and knowledge document cluster analysis for enterprise R&D strategic planning
Int. J. Technol. Manage.
Cited by (5)
Intelligent collaborative patent mining using excessive topic generation
2019, Advanced Engineering InformaticsCitation Excerpt :Technology concepts for a given domain are multivariate and are spread across topics. Subject matter expertise and vector space models such as Term Frequency-Inverse Document Frequency (TF-IDF) or Normalized TF-IDF weights are the most popular methods used to investigate the terminology of key technologies [7,8]. These investigative methods tend to lose semantic co-occurrences of terms and lead to subjective results [9].
Utilizing text mining and Kansei Engineering to support data-driven design automation at conceptual design stage
2018, Advanced Engineering InformaticsCitation Excerpt :Yoon et al. [42] proposed a semi-automated method to discern technological opportunities by integrating morphology analysis and text mining that contributes to suggest a semi-automated normative method for technology forecasting by combining morphology analysis and text mining. Trappey and Trappey [30] further utilized text mining to extract key words and phrases in legal documents to trace the evolutionary trend. Mashhadi et al. [20] applied text mining and regression analysis to examine the relationship between consumer experiences and future purchase behaviors.
A twenty-year review of brand and customer loyalty patents and academic literature
2022, Handbook of Research on Customer LoyaltyEffect of online collective intelligence in wine industry: Focus on correlation between wine quality ratings and on-premise prices
2021, Sustainability (Switzerland)Patent Analysis of Key Technologies for Smart Retailing and their Projected Economic Impact
2018, Proceedings of the 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design, CSCWD 2018