Full screen

Share

Show pages

AI for Discovery & Literature Review https://libguides.kennesaw.edu/AI4LR/about


Literature Review for Dissertation or Thesis Writers

Dissertation’s literature review: https://libguides.kennesaw.edu/lr

Searching with AI: 

Presented by Dr. Koz

Want to create interactive content? It’s easy in Genially!

Over 30 million people create interactive content in Genially

Check out what others have designed:

Transcript

AI for Discovery & Literature Review https://libguides.kennesaw.edu/AI4LR/about

Literature Review for Dissertation or Thesis Writers

Dissertation’s literature review: https://libguides.kennesaw.edu/lr

Searching with AI:

Presented by Dr. Koz

https://libguides.kennesaw.edu/lit_search

Systematic or integrative review, "systematized traditional review"

Concept Paper; LR as a learning assignment; research planning stage

Phases

•Set up Articles Alerts •RSS Feeds• *Topical journals and conferences •Monitoring academic social networking sites

Monitoring

•Plan and structure the process of searching •Maintain consistency in searching (e.g. search terms, filters •Document the search process and results

Systematic Search

•Develop a topic or a research question, and plan the systematic search •Get familiar with concepts in the field of study and with sources for evidence/literature (databases, indexes, etc.)

Preliminary Search

Strategies

Phases of Searching for the Literature

Elements of the protocol

Planning the literature Review

Protocol or a search & analysis plan

What?

How?

Where?

* Concepts; types of publications: *Level of evidence

Search strategies & techniques; types of evidence retrieval

Citation indexes, collections, repositories, and databases (IEEE, ACM, Scopus, Emerald) Academic Search Engines and OA repository (with AI agents)

Planning the Search (What? How? Where?)

What are we looking for?

Inclusion/Exclusion

Level of Evidence

Types of Publications

Concepts, Variables

What?

What?

Citation Indexes assign an index term, subject term, descriptor, topic, or category that helps you to collect relevant to your query references.

From concepts to search terms

List of databases with a thesaurus and tutorials how to do this search by a database

https://libguides.kennesaw.edu/search_tech/concept

ConceptSearching or ThesaurusBrowsing

https://libguides.kennesaw.edu/litMap/concepts

https://libguides.kennesaw.edu/Research_Plan/topic

Conceptual Framework

Topic Development

More about the Thesaurus Browsing

Contextual literature/ Positioning research

Theoretical or concept papers

Research Reports (primary research, empirical studies)

Types of Publications

Example of the evidence level

Finding Research Study Reports

  • EBSCO Discovery (SuperSearch)
  • Google Scholar,
  • Semantic
  • AI-based

Where?

Where?

Search Engines

•Web of Science, Scopus, Academic Search Ultimate

Multidisciplinary Citation Indexes and Databases

• PsycInfo, IEEE, SocIndex •List of the databases with a thesaurus https://libguides.kennesaw.edu/search_tech/concept

Disciplinary - Subject IndexesThesaurus

Limited use

Search by a subject or a title

https://library.kennesaw.edu

KSU Library Page

KSU Library Search Box

Where to start?

College of Education Library portal

Subject directory of sources for the College of Education, organized by the typical search strategy:

Where to find databases or sources?

*Recall – a measure of the quantity of relevant results a search returns. *Precision – a measure of the quality of relevant results *Level of evidence - the relevant value of the evidence *The source of the evidence is important!

Prompt engineering might improve information or knowledge retrieval from raw LLM but not evidence retrieval. RAG or FineTuning or SLM are better choices

Raw LLMs or GPT are not intended to search for "evidence." However, hybrid search engines, which capitalize on NLP and ML, offer different experiences in evidence retrieval.

LLM & GPT for evidence search: myths

Type of search or retrieval based on the type of data

Hybrid or Conversational

Lexical search

Data = Retrieval

LLM

Knowledge Graph

Semantic search

Thesaurus browsing /Subject search

Licensed data - indexes

Non-licensed or OA, shadow libraries

Where is the data coming from?

Type of Search

Comparison of AI-based academic search tools

https://libguides.kennesaw.edu/AI4LR/se

Hybrid

Semantic

Generative AI

Scite.ai, Consensus, Ellicit

Gemini, Bing, CoPilot

Semantic Scholar, Dimensions, Google Scholar

https://libguides.kennesaw.edu/SE

AI-based Search Engines

How?

Natural Language

Pearl Growing

Semantic

Boolean

Citation Chaining

Thesaurus browsing

Keywords

How?

https://libguides.kennesaw.edu/search_tech

How?Search Techniques

Related Theories & Methods

Pearl- Growing

Source or Database

Journals

Concepts & Subjects

Pearl (A relevant article)

Pearl (An article)

References & Citations

Search for similar documents based on the ”pearl” metadata. From the initial pearl or a seed (article), grow (collect) other pearls.

Research Rabbit - pearl growing or a seed paper

Click in Cited by to see all works that cited the original publication

Learn more about citation chaining https://libguides.kennesaw.edu/search_tech/chain

Citation-Chaining Indexes such as Web of Science, Scopus, or a search engine like Google Scholar allow you to see the number of citations and find who cited the publication to find seminal works and the newest research.

Keep in mind, new research will have low citation count for 2 years

The most cited work

ScopusCitation Overview/ Scopus AI

Citation Chaining using AI tools

Some hybrid and semantic search engines allow basic filters. Check Advanced search

Filters based on Inclusion/Exclusion Criteria

Protocol

Systematic Search

  • Not an exhaustive review
  • Selective, representative

When to Stop to Search?

Next page

genially options