About Hoodie

What Hoodie Provides

• Teacher and supervisor profiles that combine course, research, school, rating, review, and public academic signals.
• Community review workflows designed for students choosing courses, supervisors, research groups, and academic opportunities.
• Member tools for comparing teachers, reading full review context, and using quick lookup through the Hoodie Chrome extension.
• AI-assisted profile summaries, tags, dimension scores, and evidence notes that make large amounts of review and public-source information easier to understand.

Our Approach

Hoodie is built to keep academic discovery practical, transparent, and student-focused. Education certification is limited to school-domain signals from education email registration or Google school-domain login.

We treat Hoodie as a decision-support platform rather than an official judgement system. User reviews, public-source search evidence, and AI outputs can contain mistakes or missing context, so important academic decisions should still be checked against official school information and your own judgement.

Scoring Methodology

Hoodie uses AI large language models to analyse available teacher information across structured dimensions. The model extracts signals from user reviews, teacher metadata, and selected public-source evidence, then estimates sub-dimension scores with confidence and evidence notes. Different sub-dimensions carry different weights depending on their relevance and risk level. Dimension scores are calculated from these weighted signals, and the final overall score is produced through a weighted average across the available dimensions.

Verified school-domain reviews can carry stronger influence than unverified reviews. Risk-related signals, such as harassment, discrimination, power abuse, academic integrity concerns, or authorship unfairness, are designed to be surfaced clearly and not hidden by unrelated positive feedback.

Scoring Dimensions

• Academic reputation: publication and citation signals, research projects, academic honours, public integrity records, funding, and research resources.
• Mentorship quality: response speed, feedback quality, accessibility, meeting frequency, guidance depth, autonomy, respect, and inclusion.
• Teaching charisma: clarity, engagement, course organisation, classroom interaction, and how easy the teaching is to follow.
• Assessment friendliness: exam difficulty, grading friendliness, attendance policy, continuous assessment load, and grading transparency.
• Resource openness: access to recordings, slides, notes, reference materials, and whether course resources are updated.
• Growth and career support: knowledge gain, skill training, recommendation letters, project opportunities, industry networks, internships, jobs, applications, and alumni outcomes.
• Funding and welfare: stipend level, funding stability, travel or conference support, equipment, office conditions, and achievement rewards.
• Pressure and environment: working hours, graduation delay risk, emotional stability, team atmosphere, and respect for personal boundaries.
• Ethics and character: authorship fairness, respect for students, power boundaries, harassment or discrimination reports, corruption, and other misconduct signals.

Information Sources

• User-generated reviews: student comments, ratings, review helper answers, and whether the reviewer is school-domain verified.
• Teacher metadata: school, department, title, courses, research areas, teacher role, and profile information submitted through Hoodie or managed by administrators.
• Public academic evidence: selected public web/search evidence about publications, citations, projects, honours, integrity signals, funding, resources, or alumni outcomes where available.
• AI extraction and aggregation: large language model analysis that converts review text and public evidence into dimension-level signals, confidence values, tags, summaries, and weighted score estimates.

Company

Hoodie Academic Community is powered by Advanced Additive Manufacturing Technology LTD.