HYPE: Topic Detection in Customer Reviews
Detecting and organizing topics in customer reviews with BERTopic and language models.
Data Science and Engineering2025–2026 · Current edition
Applied Data
Science Project.
From AI concepts to
real-world solutions.
Learn to design, develop and communicate an AI project, with management supporting every step.
The project mindset · Four foundations
01
Design
User needs & requirements
02
Develop
Data, models & validation
03
Communicate
Results & impact
ManageAcross every stage
Planning · Coordination · Resources · KPIs · Risks
Design, develop and communicate. Manage throughout.
- Course credits
- 8 CFU
- Lectures
- 26 hours
- Laboratory
- 54 hours
- Teaching language
- English
- When
- 1st semester · Year 2
The courseLearn by building
Learn by building
something that matters.
The course is offered in the first semester of the 2nd year at Politecnico di Torino, Data Science and Engineering. The course is in English.
The main objective of the course is to develop an artificial intelligence solution using a data science approach. The project mindset has four foundations: Design, Develop, Communicate and Manage. Design defines user needs, the problem, stakeholders and requirements; Develop covers data, models, implementation, testing and validation; Communicate explains results and impact through technical and scientific communication. Manage supports all three throughout the project, with planning, coordination of people and resources, key performance indicators (KPIs) and risk management. The goal of this course is to let students face, for the first time, a long-running project and learn how to manage all project steps (problem specification, task assignment, design and implementation of the solution, testing, milestones management, writing of intermediate and final reports, result communication). Laboratory activities will give students first-hand experience in projects that make extensive use of data science methodologies in collaboration with companies and applied research institutes with an international breadth.
The learning path
Four foundations. One project.
Design, develop and communicate.
Manage supports the whole journey.
01
Design
Start with people.Understand user needs, define the problem, identify stakeholders and set clear requirements.
Explore lectures02
Develop
Build and validate.Work with data and models, implement the solution, then test and validate it against the requirements.
Explore lectures03
Communicate
Make the impact clear.Explain the results and their impact through clear technical and scientific communication.
Explore lectures04
Across every stageManage
Support every stage.Plan the project, coordinate people and resources, track key performance indicators (KPIs) and manage risks across Design, Develop and Communicate.
Explore lecturesExplore & apply
Your course toolkit.
26 hours of lectures
54 hours of hands-on laboratory
27 slide decks and 10 notebooks, in lecture order. Download the materials below to revisit each topic.
Lectures & project tools27 topics
- L01
Introduction
Course objectives, activities and the applied data science project.
- L02
Project mindset
Design, develop and communicate, with Manage supporting the whole project.
- L03
WBS and Gantt
Work breakdown structures, tasks, milestones and project planning.
- L04
Model- and data-centric projects
- L05
Foundation models
- L06
Hub of foundation models
Hugging Face models, BERT masking and named-entity recognition.
- L07
Large language models
BERT text similarity and IMDb sentiment analysis notebooks.
- L08
Transfer learning and domain adaptation
Adapting models to downstream tasks, with IMDb sentiment analysis.
- L09
PyTorch Lightning
Compare model training with PyTorch and Lightning.
- L10
Earth observation meets AI: introduction
An introduction to remote sensing and Earth observation.
- L11
Retrieval-augmented generation
- L12
Colaboratory
- L13
Earth observation meets AI: foundation models and tools
Geospatial modelling with TerraTorch and TorchGeo notebooks.
- L14
Vision-language models
CLIP embeddings, zero-shot classification and cross-modal retrieval.
- L15
Transfer learning with VLMs and version control
Two slide decks: VLM adaptation and Git. PEFT and LoRA practice in the notebook.
- L16
Multimodal large language models
- L17
Artificial intelligence ethics
- L18
Project proposals
- L19
Human-centred design: introduction
Principles and tools for designing around people.
- L20
Human-centred design: stakeholder mapping
- L21
Functional requirements and diagrams
- L22
Zero-shot multimodal large language models
BLIP-2 image captioning, visual question answering and classification.
- L23
Human-centred design: personas, HMW and value propositions
User personas, How Might We questions and value propositions.
- L24
Agents with Ollama and LangGraph
- L25
Sustainable Development Goals and project examples
Project impact, targets, indicators and data science applications.
- L26
Slides and project presentations
- L27
Reports: papers and deliverables
Try another topic.
Adjust your search or choose another foundation.
Put it into practice
In the laboratory.
Work with people, models and data.
Then bring them together in your team project.
- Project proposals1.5h
- User-centred application3h
Stakeholder maps, user personas and user journeys.
- Commercial neural models6h
SDKs, REST APIs and prompt engineering.
- Open-source models with Ollama3h
- Team project development40.5h
Made by ADSP students
Ideas put to work.
Explore projects from 2025–2026.
See how the course comes together.
FPT Cost Brain: AI-Assisted R&D Cost Estimation
Estimating product development costs from technical requests using machine learning and historical projects.
Lavazza AI Personas for Consumer Insights
Conversational AI personas grounded in customer segmentation research for market insights and idea validation.
ARTLM: Automated Artwork Metadata Generation
Generating structured artwork metadata from images with multimodal language models.
DINOv3 for Damage Assessment
Exploring DINOv3 for automated damage assessment.
Multimodal Emotion Recognition with Audio-Language Models
Recognizing emotions from speech and transcripts with audio-language models and efficient fine-tuning.
Multimodal Wildfire Burned Area Prediction
Predicting wildfire burned areas from pre-fire satellite imagery, terrain, weather and infrastructure data.
Open-Vocabulary Semantic Segmentation for Remote Sensing
Segmenting remote-sensing imagery using text queries and open-vocabulary models.
Ball and Player Tracking in Padel Matches
Detecting players and the ball in padel videos to derive positional statistics and tactical insights.
Unsupervised Energy Profile Analysis
Exploring energy profiles with unsupervised learning.
Tactical Football Simulation with Reinforcement Learning
Simulating offensive football scenarios with reinforcement learning agents and configurable tactical environments.
Ontology Alignment with Natural Language Processing
Matching free-text attributes to ontology classes through candidate retrieval and cross-encoder scoring.
Before you begin
Come prepared. Stay curious.
The background knowledge and reading
to support your project.
Useful foundations.
- Statistics
- Data mining
- Machine learning and deep learning
- Python language
- Relational, NoSQL, graph databases
Course 02TXXWS · 2nd year
Data Science and Engineering
Keep learning.
Reference books and reading materials.
- Machine Learning Yearning, by Andrew Ng
- Data Science from Scratch, Joel Grus
- Harvard Business Review Project Management Handbook: How to Launch, Lead, and Sponsor Successful Projects, by Antonio Nieto-Rodriguez
- Oxford Guide to Effective Writing and Speaking: How to Communicate Clearly, by John Seely
- The Design of Everyday Things: Revised and Expanded Edition, by Donald Norman
- Noessel C. Designing Agentive Technology. AI That Works for People. Rosenfeld, 2013
- Proposal for a Regulation laying down harmonised rules on artificial intelligence, European Commission, 2021
Teaching materials are available through this website and the teaching portal.
How the course works
The course is structured in three folds:
- Introduction to the concepts to perform a project
- Introduction to the tools to put in place the concepts
- Laboratory sessions for the execution of the projects and meetups with the company key resources (project managers and project leaders) to - successfully execute the assigned projects.
Learn together
Your teaching team.
The people supporting
the 2025–2026 edition.
Giuseppe Rizzo
Course lead · AI & data science
Antonella Frisiello
Service design & UX
Alessandro Fiori
Teaching assistant
Federico D’Asaro
Teaching assistant
Luca Barco
Teaching assistant
The ADSP archive