MyMigrationBot: A Cloud-based Facebook Social Chatbot for Migrant Populations
arXiv:2208.13005 · doi:10.15439/978-83-965897-2-9
Abstract
We present the design, implementation and evaluation of a new cloud-based social chatbot called MyMigrationBot, that is deployed to Facebook. The system asks and answers questions related to user's personality traits and person-job competency fit to give feedback, and potentially support migrant populations. The chatbot's response database is based on reputable socio-psychological tools and can be customised. The system's backend is written with Node.js, deployed to AWS and Twilio, and joined with Facebook through Graph and Messenger APIs. To our knowledge this is the first multilingual social chatbot deployed to Facebook and designed to research and support migrant populations with feedback in Europe. It does not have personality like other bots, but it can study and feedback on migrants' personality and on other customised questionnaires e.g., job-competency fit. The aim of a social chatbot in our research project is to help engage migrants with social research using feedback information tailored to them. It can help migrants to get knowledge about their psycho-social resources and therefore to facilitate their integration process into a receiving labour market. We evaluated the chatbot on a group of 53 people, incl. 23 migrants, and we present the results.
arXiv comment9 pages, 5 figures, 17th Conference on Computer Science and Intelligence Systems (FedCSIS 2022)
References in corpus (40)
- Scikit-learn: Machine Learning in Python
- Distributed Representations of Words and Phrases and their Compositionality
- Overcoming catastrophic forgetting in neural networks
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Challenges, Methods, and Future Directions
- Bootstrap your own latent: A new approach to self-supervised Learning
- Character-level Convolutional Networks for Text Classification
- Federated Learning: Strategies for Improving Communication Efficiency
- A continual learning survey: Defying forgetting in classification tasks
- Universal Sentence Encoder
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- Continual Learning Through Synaptic Intelligence
- Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
- Efficient Lifelong Learning with A-GEM
- Gradient Episodic Memory for Continual Learning
- Experience Replay for Continual Learning
- FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Adaptive Safety with Control Barrier Functions
- HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
- A Berkeley View of Systems Challenges for AI
- FMA: A Dataset For Music Analysis
- Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
- An automated pipeline for the discovery of conspiracy and conspiracy theory narrative frameworks: Bridgegate, Pizzagate and storytelling on the web
- Lifelong Generative Modeling
- Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
- Train Once, Test Anywhere: Zero-Shot Learning for Text Classification
- FetchSGD: Communication-Efficient Federated Learning with Sketching
- Class-incremental learning: survey and performance evaluation on image classification
- Communication Efficient Federated Learning over Multiple Access Channels
- Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks
- A Component-Based Simplex Architecture for High-Assurance Cyber-Physical Systems
- Contrastive Learning of Musical Representations
- FEDZIP: A Compression Framework for Communication-Efficient Federated Learning
- A Survey of Asynchronous Programming Using Coroutines in the Internet of Things and Embedded Systems
- Continual Classification Learning Using Generative Models
- Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR
- Zero-Shot Audio Classification via Semantic Embeddings
- A Combined Dependability and Security Approach for Third Party Software in Space Systems