ArticleBMC psychology2026
Erudit AI SaaS: an artificial intelligence tool based on RoBERTa for classifying employee engagement.
Article in BMC psychology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Reality erosion in digital environments: the concept of digital blur and scale development.Frontiers in psychology · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundEngagement has been defined since its inception by several currents, mainly two different ones such as those of Kahn (1990) and Schaufeli (2002). Based on these two main currents, self-report instruments for its measurement have been increasing over time. However, in addition to the limitations of the instrument itself (low reliability, low use, etc.), these instruments also have limitations inherent to self-report measures in general (social desirability, correction time, etc.). To solve this problem, and taking into account that the way of communicating through corporate tools in companies (slack, Gmail, Microsoft teams, etc.,) has increased considerably, this study proposes the validation of an artificial intelligence tool (Erudit AI SaaS) that allows to know the level of engagement of employees by analyzing the text they write in their corporate tools.
methodsTo test whether the tool is really assessing the level of engagement we compared the self-report instruments UWES-9 and JRA with the Erudit AI SaaS. Thirty-five employees were selected as participants for the study and the instruments were administered on five different occasions. To determine convergent and divergent validity, bivariate correlations were performed, in the case of reliability, this was calculated using intraclass correlation indexes.
resultsThe results showed good results for convergent validity between the Erudit AI SaaS and the self-report instruments UWES-9 and JRA. Divergent validity also yielded good results between the Erudit AI SaaS and MBI. The reliability, however, was moderate.
conclusionsThese findings provide preliminary evidence supporting the construct validity of Erudit AI SaaS for estimating employee engagement through textual data extracted from corporate communication platforms. However, while initial validity and reliability are encouraging, further research with larger samples and more robust statistical analyses is needed to generalize the results and strengthen the tool’s psychometric foundation.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.