Kicked off #Etmaal2025 with a nice workshop on systematic review automation using ASReview!
February 3, 2025 at 11:05 AM
Kicked off #Etmaal2025 with a nice workshop on systematic review automation using ASReview!
More than AI,I recommend active learning. In that sense, ASReview does a great job:
asreview.nl
asreview.nl
ASReview – Active learning for Systematic Reviews
asreview.nl
October 15, 2024 at 7:09 PM
More than AI,I recommend active learning. In that sense, ASReview does a great job:
asreview.nl
asreview.nl
Its not as good as active learning tools eg ASReview but that's not zero shot. Among zero shot classifers I think modern large llms as screeners beats it? but are much more expensive of course... /2
September 24, 2026 at 3:17 PM
Its not as good as active learning tools eg ASReview but that's not zero shot. Among zero shot classifers I think modern large llms as screeners beats it? but are much more expensive of course... /2
"These findings suggest that the evaluated ASReview configurations may be insufficient for reviews in which near-complete retrieval of relevant evidence is required"
August 24, 2026 at 12:56 AM
"These findings suggest that the evaluated ASReview configurations may be insufficient for reviews in which near-complete retrieval of relevant evidence is required"
ASReviewの評価
Performance of Two AI Approaches in ASReview Compared With Manual Screening for Dementia Care Literature Screening: Comparative Analysis. JMIR Form Res. 2026 Aug 20. 10 e84989 doi.org/10.2196/84989
Performance of Two AI Approaches in ASReview Compared With Manual Screening for Dementia Care Literature Screening: Comparative Analysis. JMIR Form Res. 2026 Aug 20. 10 e84989 doi.org/10.2196/84989
doi.org
August 24, 2026 at 12:56 AM
ASReviewの評価
Performance of Two AI Approaches in ASReview Compared With Manual Screening for Dementia Care Literature Screening: Comparative Analysis. JMIR Form Res. 2026 Aug 20. 10 e84989 doi.org/10.2196/84989
Performance of Two AI Approaches in ASReview Compared With Manual Screening for Dementia Care Literature Screening: Comparative Analysis. JMIR Form Res. 2026 Aug 20. 10 e84989 doi.org/10.2196/84989
Yes - I've used ASreview and I love it (asreview.nl). It uses ML to present you with more relevant papers earlier on, and then you only screen until a stopping role. You train the model yourself. Free! Open Source!
ASReview – Active learning for Systematic Reviews
asreview.nl
September 19, 2024 at 3:20 PM
Yes - I've used ASreview and I love it (asreview.nl). It uses ML to present you with more relevant papers earlier on, and then you only screen until a stopping role. You train the model yourself. Free! Open Source!
Some cool tools for #SystematicReviews:
asreview.nl (obtain an overview of most relevant records efficiently while being transparent in the process)
www.cadima.info (free web tool facilitating and assuring documentation of systematic reviews, systematic maps, & other literature reviews)
asreview.nl (obtain an overview of most relevant records efficiently while being transparent in the process)
www.cadima.info (free web tool facilitating and assuring documentation of systematic reviews, systematic maps, & other literature reviews)
ASReview - Active learning for Systematic Reviews
Our software ASReview is designed to accelerate the step of screening abstracts and titles with a minimum of papers to be read.
asreview.nl
November 27, 2024 at 10:58 PM
Some cool tools for #SystematicReviews:
asreview.nl (obtain an overview of most relevant records efficiently while being transparent in the process)
www.cadima.info (free web tool facilitating and assuring documentation of systematic reviews, systematic maps, & other literature reviews)
asreview.nl (obtain an overview of most relevant records efficiently while being transparent in the process)
www.cadima.info (free web tool facilitating and assuring documentation of systematic reviews, systematic maps, & other literature reviews)
Just discovered the SYNERGY dataset, from the ASR review team, providing the full screening data (list of articles with binary included/excluded variables, abstract titles and so on) from 26 systematic reviews!!!
Thank you. So. Much.
github.com/asreview/syn...
#episky #openscience
Thank you. So. Much.
github.com/asreview/syn...
#episky #openscience
GitHub - asreview/synergy-dataset: SYNERGY - Open machine learning dataset on study selection in systematic reviews
SYNERGY - Open machine learning dataset on study selection in systematic reviews - asreview/synergy-dataset
github.com
February 3, 2025 at 4:42 PM
Just discovered the SYNERGY dataset, from the ASR review team, providing the full screening data (list of articles with binary included/excluded variables, abstract titles and so on) from 26 systematic reviews!!!
Thank you. So. Much.
github.com/asreview/syn...
#episky #openscience
Thank you. So. Much.
github.com/asreview/syn...
#episky #openscience
Online Now: ASReview LAB v.2: Open-source text screening with multiple agents and a crowd of experts #datascience
ASReview LAB v.2: Open-source text screening with multiple agents and a crowd of experts
ASReview LAB v.2 enables efficient, transparent AI-assisted systematic reviews by combining multiple machine learning models with input from expert crowds. Users can switch between fast, general-purpose, and domain-specific models within the same project. Leveraging the SYNERGY benchmark, version 2 improves performance by 24.1%. The open-source platform paves the way for scalable, collaborative knowledge curation and demonstrates how AI can support expert judgment in high-stakes decision-making across science, medicine, and policy.
dlvr.it
July 3, 2025 at 7:46 PM
Online Now: ASReview LAB v.2: Open-source text screening with multiple agents and a crowd of experts #datascience
Just attended today's #LABTalk at @uni-muenster.de! Our colleague Nicole Niehoff shared her approach to conducting a systematic review using #ASReview & #ChatGPT, offering valuable insights into her experiences with these cutting-edge tools.
September 4, 2025 at 1:19 PM
Just attended today's #LABTalk at @uni-muenster.de! Our colleague Nicole Niehoff shared her approach to conducting a systematic review using #ASReview & #ChatGPT, offering valuable insights into her experiences with these cutting-edge tools.
Really interesting is also the use of LLM+CAL (continously active learning) in this ceur-ws.org/Vol-3770/pap... . Its a bit complicated with 2 phases but the general idea is to sample first from LLM judgements. ASReview samples from papers LLM judge true or unknown +100 random LLM judge false
ceur-ws.org
October 25, 2025 at 4:37 PM
Really interesting is also the use of LLM+CAL (continously active learning) in this ceur-ws.org/Vol-3770/pap... . Its a bit complicated with 2 phases but the general idea is to sample first from LLM judgements. ASReview samples from papers LLM judge true or unknown +100 random LLM judge false
Authors are permitted to use tools to help automate paper selection. AI tools, when used at any stage in manuscript preparation, must be declared per Elsevier policies. Use of open source tools is encouraged (see e.g. the recent paper on ASReview 2.0 www.cell.com/patterns/ful...). 7/n
November 20, 2025 at 2:50 PM
Authors are permitted to use tools to help automate paper selection. AI tools, when used at any stage in manuscript preparation, must be declared per Elsevier policies. Use of open source tools is encouraged (see e.g. the recent paper on ASReview 2.0 www.cell.com/patterns/ful...). 7/n
Great workshop about ASReview (look it up 👀) When AI can help you save incredible amount of time when doing systematic literature reviews⏱️ #evidencegeneratio #systematicreview #AI #ML #data
January 22, 2025 at 11:32 AM
Great workshop about ASReview (look it up 👀) When AI can help you save incredible amount of time when doing systematic literature reviews⏱️ #evidencegeneratio #systematicreview #AI #ML #data
For openalex they did vector embeddings using 1)inclusion criteria 2)abstracts of included 34 studies 3) train ASReview with included 34 studies to produce logistic model which is used to score abstracts. In each method they took some top k
October 25, 2025 at 4:09 PM
For openalex they did vector embeddings using 1)inclusion criteria 2)abstracts of included 34 studies 3) train ASReview with included 34 studies to produce logistic model which is used to score abstracts. In each method they took some top k
To be clear if you believe ES must involve screening every single of your search results, then obviously yes, ranking doesnt matter! But even in ES, peeps are doing active learning with ASreview, stopping before everything is screened. Relevancy ranking is crazy important here! (3)
March 31, 2026 at 1:20 AM
To be clear if you believe ES must involve screening every single of your search results, then obviously yes, ranking doesnt matter! But even in ES, peeps are doing active learning with ASreview, stopping before everything is screened. Relevancy ranking is crazy important here! (3)
Fascinating, thanks! “The AI companies didn’t focus on PDF, because PDF is very hard, until they realized that, well, it turns out a lot of the really high-quality stuff is in fact in PDF, and so now we have to deal with it.”
This makes me wonder about ASReview and other apps.
This makes me wonder about ASReview and other apps.
March 3, 2026 at 5:57 PM
Fascinating, thanks! “The AI companies didn’t focus on PDF, because PDF is very hard, until they realized that, well, it turns out a lot of the really high-quality stuff is in fact in PDF, and so now we have to deal with it.”
This makes me wonder about ASReview and other apps.
This makes me wonder about ASReview and other apps.
Looking to level up your systematic review skills?
Join our #KOMEX2026 course by Dr Liliana Abreu @uni-konstanz.de and learn to formulate review Qs, appraise quality, and use ASreview for AI-supported screening.
📅 19–20 Feb
💻 Online
€180 early bird
Sign up: afww.uni-konstanz.de/en/microcred...
Join our #KOMEX2026 course by Dr Liliana Abreu @uni-konstanz.de and learn to formulate review Qs, appraise quality, and use ASreview for AI-supported screening.
📅 19–20 Feb
💻 Online
€180 early bird
Sign up: afww.uni-konstanz.de/en/microcred...
October 20, 2025 at 3:51 PM
Looking to level up your systematic review skills?
Join our #KOMEX2026 course by Dr Liliana Abreu @uni-konstanz.de and learn to formulate review Qs, appraise quality, and use ASreview for AI-supported screening.
📅 19–20 Feb
💻 Online
€180 early bird
Sign up: afww.uni-konstanz.de/en/microcred...
Join our #KOMEX2026 course by Dr Liliana Abreu @uni-konstanz.de and learn to formulate review Qs, appraise quality, and use ASreview for AI-supported screening.
📅 19–20 Feb
💻 Online
€180 early bird
Sign up: afww.uni-konstanz.de/en/microcred...
気になっているASReviewを使った調査👀
Comparing the performance of narrow vs. broad search strategies when using machine learning-based software for title/abstract screening
doi.org/10.5195/jmla...
Comparing the performance of narrow vs. broad search strategies when using machine learning-based software for title/abstract screening
doi.org/10.5195/jmla...
Comparing the performance of narrow vs. broad search strategies when using machine learning-based software for title/abstract screening
| Journal of the Medical Library Association
doi.org
April 19, 2026 at 9:45 PM
気になっているASReviewを使った調査👀
Comparing the performance of narrow vs. broad search strategies when using machine learning-based software for title/abstract screening
doi.org/10.5195/jmla...
Comparing the performance of narrow vs. broad search strategies when using machine learning-based software for title/abstract screening
doi.org/10.5195/jmla...
Had a very pleasant afternoon at the ASReview user meeting today. The following paper about stopping rules when screening with the help of LLM looks very interesting: systematicreviewsjournal.biomedcentral.com/articles/10....
The SAFE procedure: a practical stopping heuristic for active learning-based screening in systematic reviews and meta-analyses - Systematic Reviews
Active learning has become an increasingly popular method for screening large amounts of data in systematic reviews and meta-analyses. The active learning process continually improves its predictions ...
systematicreviewsjournal.biomedcentral.com
January 30, 2025 at 7:48 PM
Had a very pleasant afternoon at the ASReview user meeting today. The following paper about stopping rules when screening with the help of LLM looks very interesting: systematicreviewsjournal.biomedcentral.com/articles/10....
Thanks - hearing good things about ASReview
www.nature.com/articles/s42...
asreview.nl
Unclear to me, though, how you decide when to stop manually screening
www.nature.com/articles/s42...
asreview.nl
Unclear to me, though, how you decide when to stop manually screening
An open source machine learning framework for efficient and transparent systematic reviews - Nature Machine Intelligence
It is a challenging task for any research field to screen the literature and determine what needs to be included in a systematic review in a transparent way. A new open source machine learning framewo...
www.nature.com
September 19, 2024 at 4:44 PM
Thanks - hearing good things about ASReview
www.nature.com/articles/s42...
asreview.nl
Unclear to me, though, how you decide when to stop manually screening
www.nature.com/articles/s42...
asreview.nl
Unclear to me, though, how you decide when to stop manually screening
followthemoney har nettopp åpnet repoet followthemoney/asr: https://github.com/followthemoney/asr
Arkiv for ASReview
Arkiv for ASReview
July 7, 2026 at 1:28 PM
followthemoney har nettopp åpnet repoet followthemoney/asr: https://github.com/followthemoney/asr
Arkiv for ASReview
Arkiv for ASReview
Optimizing ASReview simulations: A generic multiprocessing solution for 'light-data' and 'heavy-data' users: http://osf.io/9h5ju/
November 3, 2023 at 1:52 PM
Optimizing ASReview simulations: A generic multiprocessing solution for 'light-data' and 'heavy-data' users: http://osf.io/9h5ju/
Optimizing ASReview simulations: A generic multiprocessing solution for 'light-data' and 'heavy-data' users: http://osf.io/mh4vt/
November 3, 2023 at 1:43 PM
Optimizing ASReview simulations: A generic multiprocessing solution for 'light-data' and 'heavy-data' users: http://osf.io/mh4vt/
Would be interested to hear how you derrived a stopping rule. That seems to be the key decision to make using this approach.
Also, in standard reviews, you adopt double screening for at least a portion of titles and abstracts. Unclear to me how that works in the ASReview framework?
Also, in standard reviews, you adopt double screening for at least a portion of titles and abstracts. Unclear to me how that works in the ASReview framework?
September 20, 2024 at 10:45 AM
Would be interested to hear how you derrived a stopping rule. That seems to be the key decision to make using this approach.
Also, in standard reviews, you adopt double screening for at least a portion of titles and abstracts. Unclear to me how that works in the ASReview framework?
Also, in standard reviews, you adopt double screening for at least a portion of titles and abstracts. Unclear to me how that works in the ASReview framework?
Article selection after the search is sped up greatly by Smarter Systematic Reviews with Open-Source AI | ASReview share.google/AjNRVes9TpaS...
ASReview - Active learning for Systematic Reviews
Our software ASReview is designed to accelerate the step of screening abstracts and titles with a minimum of papers to be read.
share.google
April 28, 2026 at 5:03 AM
Article selection after the search is sped up greatly by Smarter Systematic Reviews with Open-Source AI | ASReview share.google/AjNRVes9TpaS...