| Row ID | Full name in Chinese/中文全名 | Full name in English/英文全名 | Gender/性別 | Current Year of Study/目前就讀的年級 |
|---|---|---|---|---|
| 1 | 李悅 | LI YUE | Female/女性 | Grade 10 (Secondary 4)/中學十年級（中四） |
| 2 | 伍詠禧 | NG WING HEI | Female/女性 | Grade 10 (Secondary 4)/中學十年級（中四） |
| 3 | 陳靜瑤 | CHAN CHING YIU | Female/女性 | Grade 10 (Secondary 4)/中學十年級（中四） |
Teenagers in daily life are often exposed to drug-related terminology or emoticons on social media sites. Their lack of taste could make them curious and unintentionally veers off course. Drug sellers might refer to marijuana as "new tea," "flying," or even use emojis like ✔️ as covert signals, for instance. Teenagers find it difficult to identify these hidden terms and symbols, which increases their risk of unintentional drug use, therefore compromising their physical and mental health, academic performance, and family connections. Furthermore, conventional drug prevention education moves slowly and cannot keep up with the often changing lingo used by traffickers, therefore reducing the efficacy in prevention.
The answer is to create an AI-based drug prevention education platform including the following technologies:
Natural language processing (NLP) uses keyword frequency detection and context analysis to find new slang phrases (such as "universe fuel," used to describe synthetic cannabinoids).
Examining the link between emojis and words (e.g., ✔️ + "flying" as a code for marijuana) and aggregates contextual data helps one to evaluate risk levels.
Constant learning and knowledge graphs dynamically update the terminology database and link it to known drug-related facts (e.g., linking "K仔" with the ketamine hazards).
Graph neural networks (GNNs) are used to examine users' social networks, therefore automatically informing law enforcement authorities about high-risk accounts (e.g., those routinely publishing coded language at night).
To facilitate data collecting, the fundamental technologies consist in Python programming, TensorFlow machine learning frameworks, and connection with social media APIs.
For the following reasons this method is the best one:
-Real-time and adaptive: AI can rapidly pick up new slang jargon, therefore tackling the difficulty of traffickers always shifting their lingo more quickly than conventional hand updates.
-Combining data including language, emojis, and user behavior, the system covers all covert strategies used by traffickers, hence reducing misjudging rates.
-An automated risk assessment and reporting system—such as passing low-risk instances to school social workers and high-risk users to law enforcement—helps law enforcement and educational initiatives be more efficient.
-Sustainable Education: The platform provides an interactive drug information database designed to assist youngsters learn over time, therefore lowering their curiosity and the risk of accidental exposure at its source.
The AI-based strategy combines technological accuracy with social cost-effectiveness unlike static outreach tools or manual monitoring.
Personal Information Collection Statement (PICS)/收集個人資料聲明:
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.
- I have read and agree to the competition rules and privacy policy/我已閱讀並同意比賽規則和隱私權政策。