Site Logo
All articles
Commentary on News

AI-enabled qualitative analysis: sand mining in Ghana

Evidano6 min read

AI-enabled qualitative analysis is the primary keyword of this post and the lens we use to translate a new qualitative study into actionable research workflows. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. According to the PLOS ONE paper, published on August 13, 2026, researchers interviewed 32 sand-mining stakeholders and ran FGDs to assess how Ghana’s legal framework is applied at the local level; the study found systemic enforcement gaps that enable illegal extraction. This post explains what the PLOS ONE study measured, pulls the exact statistics you can cite, and shows how AI-driven coding, transcription, and cross-segment analysis speed evidence-to-policy work for research teams and regulators.

Key Takeaways

According to the PLOS ONE study, published August 13, 2026, researchers conducted 32 key informant interviews and FGDs in two Ghanaian districts to analyse attitudes toward sand-mining regulation (PLOS ONE).

  • 32 interviews and multiple FGDs were completed between March 3, 2021 and May 20, 2021, with follow-up interviews from January 10 to January 21, 2022, according to the PLOS ONE paper.
  • The PLOS ONE study reports that over 80% of sand mining in Ghana is illegal, a figure cited in the paper’s introduction and literature review (Asare et al., 2026).
  • The research area yields an estimated 4.55 million cubic metres of sand annually from the two districts, as reported in the PLOS ONE methods section.
  • Regulatory bottlenecks identified in the PLOS ONE paper include understaffing, outdated sanctioning (for example the GHS 200 fine noted in 2021), and fragmented agency coordination.

What happened and how the study measured it

The PLOS ONE study analysed actors’ attitudes toward sand-mining law application by combining 32 purposive key informant interviews, two focus group discussions per site, and documentary review, as described in Asare et al., 2026.

According to the PLOS ONE paper, data collection ran from March 3, 2021 to May 20, 2021 with additional follow-up interviews from January 10 to January 21, 2022, and the authors used NVivo 12 for thematic content analysis.

According to the PLOS ONE results, the authors identified 57 themes and reported that license, compensation, complaint channels, and stakeholder participation rules are poorly enforced; the authors explicitly linked enforcement gaps to staffing shortages, outdated systems, rent-seeking, and political patronage.

Direct quotations from the PLOS ONE study illustrate perceptions in the field: a landowner said, "Most landowners believe that while the lands belong to them, regulatory agencies accrue gains from sand mining" (Landowner in Gomoa Buduatta, 2021), an EPA official stated, "The sanction for sand mining offenses... is GHS 200 ($20)" (Key informant, 2021), and a MINCOM official described a "blame game" among agencies (MINCOM, 2021).

Findings snapshot

Date / PeriodMetricValue (reported)Implication
March 3–May 20, 2021; Jan 10–21, 2022Fieldwork periodPrimary interviews and FGDsQualitative saturation reached after 32 interviews, per PLOS ONE
Published August 13, 2026PublicationPLOS ONE article (Asare et al., 2026)Peer-reviewed evidence base for governance recommendations
2026 (study cites prior literature)Illegal extraction rate>80%Majority of sand extraction occurs outside formal permits
Data reported in methodsLocal extraction volume4.55 million m3/yearHigh supply pressure to nearby Accra markets
Key informants, 2021Penalty for noncompliance under LI 1652GHS 200 (~$20)Penalty judged too low to deter illegal mining
Study analysis, 2026Themes identified57 themesExtensive thematic saturation in qualitative dataset

Implications for researchers and policy analysts

Researchers should treat Ghana’s sand-mining governance as a polycentric system where legal texts, local chiefs, contractors, and state regulators interact, as framed by the PLOS ONE authors referencing Ostrom (2010).

According to the PLOS ONE study, enforcement deficits are driven by understaffing and weak inter-agency coordination; researchers designing comparative governance studies should therefore gather documents, interview regulators, and map actor networks to capture these dynamics.

According to Asare et al., 2026, low fines and bureaucratic licensing processes distort incentives; policy analysts should quantify sanction levels and processing times as part of any reform evaluation.

How Evidano helps: practical AI workflows for qualitative sand-mining research

Problem: fragmented, slow synthesis of interviews

Answer: AI tools speed coding and cross-segment comparisons so teams can move from transcripts to recommendations in days, not months.

According to the PLOS ONE study, 32 interviews plus FGDs produced 57 themes; with Evidano you can ingest transcripts, run AI-assisted thematic coding, and surface top themes and verbatim quotes for policy briefs.

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. See our features page for relevant capabilities.

Problem: transcription quality and multi-language fieldwork

Answer: Accurate transcripts with custom dictionaries reduce error and preserve local terms for coding.

According to the PLOS ONE paper, the study relied on recorded interviews and careful transcription; Evidano’s speech-to-text supports custom dictionaries and PII redaction to match ethical protocols.

Problem: tracing complaints and stakeholder positions across segments

Answer: Cross-segment frequency and co-occurrence analyses show which actors raise which issues and where enforcement gaps cluster.

According to Asare et al., 2026, stakeholder marginalisation and information asymmetry were central findings; Evidano’s thematic and cross-segment tools let you compare landowners, regulators, and contractors side-by-side.

FAQ: AI-enabled qualitative analysis

What is AI-enabled qualitative analysis and why use it for sand-mining interviews?

Answer: AI-enabled qualitative analysis uses machine learning to assist human coding, pattern detection, and summarization of textual data.

According to methods described in the PLOS ONE paper, thematic coding produced 57 themes from 32 interviews; AI-assisted workflows reproduce consistent code maps faster and make cross-segment counts reproducible for policy work.

Can AI preserve direct quotations and context for policy briefs?

Answer: Yes, modern qualitative AI retains verbatim quotes and links them to coded segments for traceability.

The PLOS ONE authors relied on verbatim quotations such as "The sanction for sand mining offenses... is GHS 200 ($20)" (EPA key informant, 2021); Evidano’s exportable quote lists let you produce evidence-backed recommendations that cite original speakers and timestamps.

How do I trust AI coding compared with manual NVivo-style analysis?

Answer: Trust comes from transparent, auditable workflows: compare AI-generated codes with human double-coding and report inter-rater agreement.

According to best-practice qualitative methods cited by the PLOS ONE paper, triangulation and saturation are key; Evidano supports human-in-the-loop review so teams can validate AI codes against manual checks.

Is AI analysis ethical for sensitive interview data?

Answer: AI analysis can be ethical when platforms provide encryption, PII redaction, and restricted access.

Evidano enforces data security and PII redaction workflows and does not use customer data to train third-party models, matching the ethical confidentiality practices reported by the PLOS ONE authors.

Conclusion & Next Steps

The PLOS ONE study (Asare et al., 2026) documents enforcement, coordination, and compensation gaps that sustain illegal sand mining in Ghana and provides concrete policy recommendations such as consolidating laws and resourcing regulators.

AI-enabled qualitative analysis shortens the time from field transcripts to policy-ready evidence by automating transcription, thematic coding, and cross-segment frequency analysis while keeping verbatim quotes and audit trails.

If you run interviews or FGDs and need reproducible thematic analysis tied to direct quotes and segments, Try Evidano for free.

Topics

  • AI-enabled qualitative analysis
  • AI qualitative analysis sand mining
  • thematic analysis with AI
  • qualitative analysis Ghana sand mining

Keep reading

Browse all articles
Company
About
Newsletter

Product updates, research, and tips — straight to your inbox.

© Evidano, All Rights Reserved.