Subtopic Deep Dive

AI and Machine Learning in Knowledge Management
Research Guide

What is AI and Machine Learning in Knowledge Management?

AI and Machine Learning in Knowledge Management applies artificial intelligence algorithms and machine learning models to extract, represent, and utilize knowledge within organizational systems following the DIKW hierarchy.

This subtopic examines ML techniques for processing unstructured text into actionable insights, as in construction accident classification (Goh and Ubeynarayana, 2017; 242 citations). It covers data fusion for situation assessment (Das, 2008; 93 citations) and expert systems bridging data processing to sense-making (Malhotra, 2001; 78 citations). Over 20 papers from the provided list address text mining, big data, and fusion in knowledge-intensive domains.

Curated Papers

Key Challenges

Why It Matters

ML-driven text classification enables accident narrative analysis for safety knowledge management in construction (Goh and Ubeynarayana, 2017; Cheng et al., 2020). Data fusion techniques support high-level knowledge integration in cyber-physical systems (Das, 2008; Wang and Wang, 2016). Expert systems facilitate sense-making from raw information, improving decision processes (Malhotra, 2001). These methods scale knowledge application in Industry 4.0 and remote data environments (Andronie et al., 2022).

Key Research Challenges

Unstructured Text Processing

Extracting knowledge from narrative data requires hybrid ML models due to variability in language. Construction site accidents challenge classification accuracy (Cheng et al., 2020; 199 citations). Text mining reviews highlight data source limitations (Baek et al., 2021; 79 citations).

Scalable Data Fusion

Fusing multi-source data into situational knowledge demands level-2 fusion algorithms. Object and situation processes face computational limits (Das, 2008; 93 citations). Big data in CPS adds integration complexity (Wang and Wang, 2016; 227 citations).

Sense-Making Gap

Transitioning from information processing to human-like interpretation persists in expert systems. Knowledge management systems often fail dynamic environments (Malhotra, 2001; 78 citations). Data science debates question ML's knowledge transformation (Cao, 2020; 81 citations).

Essential Papers

Construction accident narrative classification: An evaluation of text mining techniques

Yang Miang Goh, Chalani Udhyami Ubeynarayana · 2017 · Accident Analysis & Prevention · 242 citations

Big Data in Cyber-Physical Systems, Digital Manufacturing and Industry 4.0

Lidong Wang, Guanghui Wang · 2016 · International Journal of Engineering and Manufacturing · 227 citations

A cyber physical system (CPS) is a complex system that integrates computation, communication, and physical processes.Digital manufacturing is a method of using computers and related technologies to...

Text mining-based construction site accident classification using hybrid supervised machine learning

Min‐Yuan Cheng, Denny Kusoemo, Richard Antoni Gosno · 2020 · Automation in Construction · 199 citations

High-Level Data Fusion

Subrata Das · 2008 · Allergy · 93 citations

Master cutting-edge Level 2 fusion techniques that help you develop powerful situation assessment services with eye-popping capabilities and performance with this trail-blazing resource. The book e...

Data Science: Challenges and Directions

Longbing Cao · 2020 · arXiv (Cornell University) · 81 citations

While data science has emerged as a contentious new scientific field, enormous debates and discussions have been made on it why we need data science and what makes it as a science. In reviewing hun...

Transformer-based deep learning models for adsorption capacity prediction of heavy metal ions toward biochar-based adsorbents

Zeeshan Haider Jaffari, Ather Abbas, Chang‐Min Kim et al. · 2023 · Journal of Hazardous Materials · 81 citations

A critical review of text-based research in construction: Data source, analysis method, and implications

Seungwon Baek, Wooyong Jung, Seung Heon Han · 2021 · Automation in Construction · 79 citations

Reading Guide

Foundational Papers

Start with Malhotra (2001; 78 citations) for expert systems bridging information to sense-making, then Das (2008; 93 citations) for data fusion fundamentals essential to KM hierarchies.

Recent Advances

Study Cheng et al. (2020; 199 citations) for hybrid ML in text classification and Baek et al. (2021; 79 citations) for construction text mining reviews.

Core Methods

Core techniques include supervised text mining (Goh and Ubeynarayana, 2017), big data processing in CPS (Wang and Wang, 2016), and transformer models adapted for knowledge tasks (Jaffari et al., 2023).

How PapersFlow Helps You Research AI and Machine Learning in Knowledge Management

Discover & Search

Research Agent uses searchPapers and citationGraph to map high-citation works like Goh and Ubeynarayana (2017; 242 citations) on text mining for accident classification, then findSimilarPapers reveals Cheng et al. (2020). exaSearch uncovers niche applications in construction knowledge extraction.

Analyze & Verify

Analysis Agent applies readPaperContent to parse Das (2008) fusion methods, verifyResponse with CoVe checks claims against abstracts, and runPythonAnalysis simulates text classification stats from Goh (2017) using pandas for precision/recall. GRADE grading scores evidence strength in knowledge fusion claims.

Synthesize & Write

Synthesis Agent detects gaps in sense-making coverage between Malhotra (2001) and modern ML, flags contradictions in data fusion scalability. Writing Agent uses latexEditText, latexSyncCitations for Malhotra (2001), and latexCompile to produce KM review papers with exportMermaid for DIKW workflow diagrams.

Use Cases

"Compare ML accuracy in construction accident text classification papers"

Research Agent → searchPapers → runPythonAnalysis (pandas comparison of Goh 2017 vs Cheng 2020 metrics) → statistical table output with precision scores.

"Draft LaTeX review on AI data fusion for knowledge management"

Synthesis Agent → gap detection on Das 2008 → Writing Agent → latexSyncCitations (Malhotra 2001) → latexCompile → formatted PDF with fused knowledge diagram.

"Find GitHub code for text mining in knowledge extraction"

Research Agent → citationGraph (Baek 2021) → Code Discovery (paperExtractUrls → paperFindGithubRepo → githubRepoInspect) → verified ML pipelines for construction text analysis.

Automated Workflows

Deep Research workflow conducts systematic review: searchPapers on 50+ AI-KM papers → citationGraph clustering → structured report on text mining evolution (Goh 2017 to Baek 2021). DeepScan applies 7-step analysis with CoVe checkpoints to verify fusion claims in Das (2008). Theorizer generates hypotheses on ML bridging DIKW gaps from Malhotra (2001) and Cao (2020).

Try Doxa for AI and Machine Learning in Knowledge Management Research

Frequently Asked Questions

What defines AI and ML in knowledge management?

It applies AI/ML to extract, represent, and apply knowledge per DIKW, using text mining and fusion (Goh and Ubeynarayana, 2017; Das, 2008).

What are key methods?

Hybrid supervised ML for text classification (Cheng et al., 2020), level-2 data fusion (Das, 2008), and expert systems for sense-making (Malhotra, 2001).

What are prominent papers?

Goh and Ubeynarayana (2017; 242 citations) on accident narratives, Wang and Wang (2016; 227 citations) on CPS big data, Das (2008; 93 citations) on fusion.

What open problems exist?

Scalable sense-making from data (Malhotra, 2001), handling unstructured big data in dynamic settings (Cao, 2020), and fusion in IoRT (Andronie et al., 2022).