DAGFiNN is a conversational conference assistant that can be made available for a given conference both as a chatbot on the website and as a Furhat robot physically exhibited at the conference venue. Conference participants can interact with the assistant to get advice on various questions, ranging from where to eat in the city or how to get to the airport to which sessions we recommend them to attend based on the information we have about them. The overall objective is to provide a personalized and engaging experience and allow users to ask a broad range of questions that naturally arise before and during the conference.
Features
- Provide recommendations across multiple domains, have basic conversational capabilities, and personalization integrated into a single system.
- Currently, recommenders are built for point-of-interest (POI) and conference content
- Support multiple user interfaces (UI)
- A Web chat and a Furhat robot with an optional external screen
- Use of rich responses customized to each user interface to effectively convey information.
- Utilize multiple input modalities
- Furhat is a social robot with a microphone, speaker, and camera, which makes it possible to recognize users that interacted with the robot previously.
Disclaimer
DAGFiNN is not (yet) a mature production-level system, but rather a research prototype. We welcome contributions on all levels (pull requests, suggestions for improvements, feature requests, etc.).
Demo
Citation
If you are using this repository, please cite the following paper:
@inproceedings{10.1145/3523227.3551467,
author = {Kostric, Ivica and Balog, Krisztian and Aresvik, T\o{}ll\o{}v Alexander and Bernard, Nolwenn and D\o{}rheim, Eyvinn Thu and Hantula, Pholit and Havn-S\o{}rensen, Sander and Henriksen, Rune and Hosseini, Hengameh and Khlybova, Ekaterina and Lajewska, Weronika and Mosand, Sindre Ekrheim and Orujova, Narmin},
title = {DAGFiNN: A Conversational Conference Assistant},
year = {2022},
publisher = {Association for Computing Machinery},
booktitle = {Proceedings of the 16th ACM Conference on Recommender Systems},
pages = {628–631},
series = {RecSys '22}
}
Contributors
Ivica Kostric, Krisztian Balog, Tølløv Alexander Aresvik, Nolwenn Bernard, Eyvinn Thu Dørheim, Pholit Hantula, Sander Havn-Sørensen, Rune Henriksen, Hengameh Hosseini, Ekaterina Khlybova, Weronika Lajewska, Sindre Ekrheim Mosand, Narmin Orujova