Artificial intelligence for literature reviews: opportunities and challenges

Bolaños, F. J.; Salatino, Angelo A.; Osborne, Francesco; Motta, Enrico

doi:10.1007/s10462-024-10902-3

Artif Intell Rev

2024

DOI: 10.1007/s10462-024-10902-3

|Get access via publisher |Summarize |Cite

|

Sign up to set email alerts

Artificial intelligence for literature reviews: opportunities and challenges

F. J. Bolaños

¹

,

Angelo A. Salatino

²

,

Francesco Osborne

³

et al.

Abstract: This paper presents a comprehensive review of the use of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is a rigorous and organised methodology that assesses and integrates prior research on a given topic. Numerous tools have been developed to assist and partially automate the SLR process. The increasing role of AI in this field shows great potential in providing more effective support for researchers, moving towards the semi-automatic creation of literature reviews. Our study focu… Show more

Help me understand this report

Cited by 118 publications

(13 citation statements)

References 164 publications

Supporting

0

Mentioning

13

Contrasting

0

Unclassified

0

Order By: Relevance

“…[ 122 ] emphasizes the role of AI in making a more efficient and systematic reviewing process. The adoption of AI tools for scientific research is increasingly supported by studies such as [ 123 , 124 ], which highlight how AI-based tools can simplify the process of identifying and synthesizing scientific evidence, improving both accuracy and efficiency to the point of achieving levels comparable to those of human experts. Furthermore, this approach not only significantly accelerates article selection while maintaining the same methodological rigor but also reduces the risk of human error [ 125 , 126 ].…”

Section: Resultsmentioning

confidence: 99%

Relationship Between Depression and Neurodegeneration: Risk Factor, Prodrome, Consequence, or Something Else? A Scoping Review

Papa

¹

,

Ingenito

²

,

Gal

³

et al. 2025

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

show abstract

“…[ 122 ] emphasizes the role of AI in making a more efficient and systematic reviewing process. The adoption of AI tools for scientific research is increasingly supported by studies such as [ 123 , 124 ], which highlight how AI-based tools can simplify the process of identifying and synthesizing scientific evidence, improving both accuracy and efficiency to the point of achieving levels comparable to those of human experts. Furthermore, this approach not only significantly accelerates article selection while maintaining the same methodological rigor but also reduces the risk of human error [ 125 , 126 ].…”

Section: Resultsmentioning

confidence: 99%

Relationship Between Depression and Neurodegeneration: Risk Factor, Prodrome, Consequence, or Something Else? A Scoping Review

Papa

¹

,

Ingenito

²

,

Gal

³

et al. 2025

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

show abstract

“…The prospect of employing AI tools to aid in these intensive steps is attractive, and being actively explored by many scientific groups and software tool companies (Bolaños et al, 2024; Yip et al, 2024). However, due to the goal of maximum comprehensiveness and need for a careful balance between rigor and pragmatic flexibility to handle the highly heterogeneous and nuanced nature of the fundamental biology literature, the requirement for human judgement and validation is unlikely to be replaced by AI in the immediate future.…”

Section: Discussionmentioning

confidence: 99%

A scoping study of the whole-cell imaging literature: a foundational corpus, potential for mesoscale data synthesis, and implications for standardization of an emerging field

Mirvis

¹

,

Weingard

²

,

Goodman

³

et al. 2025

Preprint

6

0

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

show abstract

“…Research that has taken place advocating AI to assist or complement the work conducted by an IS note the complexity and nuances of IS undertakings and the difficulties faced with accuracy and robustness [ 23 , 39 ]. The contributions made to the AI discussion at CORE would support this, as concerns lay in the ethical questions around using AI including data privacy and bias in AI algorithms, as well as reservations on the quality of the data, low accuracy, illegitimate referencing, reproducibility of results, and ambiguous sourcing.…”

Section: Discussionmentioning

confidence: 99%

Exploring the Role of Artificial Intelligence in Evidence Synthesis: Insights From the CORE Information Retrieval Forum 2025

Eastaugh

¹

,

Still

²

,

Beyer

³

et al. 2025

Cochrane Evidence Synthesis and Methods

0

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

show abstract

Scite is an AI-powered platform that helps researchers discover and evaluate scientific literature through Smart Citations, showing whether studies support or contradict a claim. Now part of Research Solutions, Scite has indexed 1.6B+ citations, partners with 30+ publishers, and serves 2M users worldwide.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA