How does the inference latency and classification robustness of AutoML pipelines compare to deep learning mode

Abstract

Abstract: Stress and depression are prevalent nowadays across people of all ages due to the quick paces of life. People use social media to express their feelings. Thus, social media constitute a valuable form of information for the early detection of stress and depression. Although many research works have been introduced targeting the early recognition of stress and depression, there are still limitations. There have been proposed multi-task learning settings, which use depression and emotion (or figurative language) as the primary and auxiliary tasks respectively. However, although stress is inextric

Research Question

How does the inference latency and classification robustness of AutoML pipelines compare to deep learning models when detecting adversarial spam patterns in non-English social media text?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance