A LASSO model infers students' Big-Five personality from communication behavior with significantly better accuracy than a mean baseline¶

Claim · All claims
Evidence · 1 study (2 entries) · associational r1 · q3
Currency · newest study 2019 · not yet checked against its sources · not reviewed by a person

Subclaims¶

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q3 i? LASSO achieves significantly lower prediction error than baseline across all five traits (average MAE 0.664 vs 0.852, t=-8.8, p<0.01). → Wen Wu 2019 q3 i? LASSO's average Spearman rank correlation between predicted and true trait scores is 0.594 versus -0.198 for baseline. → Wen Wu 2019 (2)

Evidence¶

Wen Wu 2019¶

Wen Wu, Li Chen, Qingchang Yang, You Li. (2019). Inferring Students' Personality from Their Communication Behavior in Web-based Learning Systems. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-018-00173-9

q3 · i? · associational · r1

Prediction experiment with 164 students, 90/10 train-test split with 10-fold cross-validation, comparing LASSO against a mean-value baseline using two-tailed paired t-tests. Statistics copied from the Prediction Results section.

"the prediction error of LASSO is significantly lower than that of baseline regarding MAE and RMSE (average MAE: 0.664 vs. 0.852, t=-8.8, p< 0.01; average RMSE: 0.842 vs. 0.900, t=-6.3, p< 0.01)."

Wen Wu 2019 (2)¶

q3 · i? · associational · r1

Spearman's rank correlation between predicted values and ground truth for the same LASSO evaluation; the article notes the closer to 1 the better. No standardized effect size printed.

"the average value of five personality traits generated by LASSO is 0.594 while the value of baseline is -0.198."

Discussion¶

Distinct communication-behavior features significantly predict each Big-Five trait, with exclamation marks and after-class activities the strongest Neuroticism predictors — a narrower finding that bears on this claim
Students' Big-Five personality significantly influences their usage of communication tools in a web-based learning system, with 32 of 120 behavioral features significantly affected — related

Page metadata

Field	Value
`type`	`claim`
`id`	`lasso-personality-prediction-communication-behavior`
`title`	`A LASSO model infers students' Big-Five personality from communication behavior with significantly better accuracy than a mean baseline`
`description`	`A LASSO model infers students' Big-Five personality from communication behavior with significantly better accuracy than a mean baseline`
`status`	`review`
`evidence_strength`	`moderate`
`newest_evidence`	`2019`
`generated`	by `process:wiki-ingest` on `2026-10-28`
`trust`	unverified — no one has confirmed this page's content
`sources`	2 — `wen-wu-2019`, `wen-wu-2019-2`

Frontmatter is the page's machine-readable record — see the Schema & Guide.