scispace - formally typeset
Proceedings ArticleDOI

Fuzzy-Based Conversational Recommender for Data-intensive Science Gateway Applications

TLDR
A novel intuitionistic fuzzy logic based conversational recommender that can provide guidance to users when using science gateways for research and education workflows and can provide step-by-step navigational support and generate distinct responses based on user proficiency is presented.
Abstract
Neuro-scientists are increasingly relying on parallel and distributed computing resources for analysis and visualization of their neuron simulations. Although science gateways have democratized relevant high performance/throughput resources, users require expert knowledge about programming and infrastructure configuration that is beyond the repertoire of most neuroscience programs. These factors become deterrents for the successful adoption and the ultimate diffusion (i.e., systemic spread) of science gateways in the neuroscience community. In this paper, we present a novel intuitionistic fuzzy logic based conversational recommender that can provide guidance to users when using science gateways for research and education workflows. The users interact with a context-aware chatbot that is embedded within custom web-portals to obtain simulation tools/resources to accomplish their goals. In order to ensure user goals are met, the chatbot profiles a user’s cyberinfrastructure and neuroscience domain proficiency level using a ‘usability quadrant’ approach. Simulation of user queries for an exemplary neuroscience use case demonstrates that our chatbot can provide step-by-step navigational support and generate distinct responses based on user proficiency.

read more

Citations
More filters
Journal ArticleDOI

A Survey on Conversational Recommender Systems

TL;DR: A detailed survey of existing approaches to conversational recommendation is provided, categorizing these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background.
Journal ArticleDOI

A Survey on Conversational Recommender Systems

TL;DR: Conversational recommender systems (CRS) as mentioned in this paper are software applications that help users to find items of interest in situations of information overload, where the user can ask questions about the recommendations and to give feedback.
Journal ArticleDOI

Evidence-Based Recommender System for a COVID-19 Publication Analytics Service

TL;DR: KnowCOVID-19 as mentioned in this paper is an evidence-based recommender system that utilizes an edge computing service to integrate recommender modules for data analytics using end-user thin-clients.
Journal ArticleDOI

If you build it, promote it, and they trust you, then they will come: Diffusion strategies for science gateways and cyberinfrastructure adoption to harness big data in the science, technology, engineering, and mathematics (STEM) community

TL;DR: This article identified seven external communication practices of science gateways and cyberinfrastructure projects and revised the pop culture line to “If You Build It, Promote It, and They Trust You, Then They Will Come.”
Journal ArticleDOI

Recommender‐as‐a‐service with chatbot guided domain‐science knowledge discovery in a science gateway

TL;DR: The OnTimeRecommend comprises of several integrated recommender modules implemented as microservices that can be augmented to a science gateway in the form of a recommender-as-a-service and is aided by a chatbot plug-in viz., Vidura Advisor.
References
More filters
Proceedings ArticleDOI

The CIPRES science gateway: a community resource for phylogenetic analyses

TL;DR: Progress in managing the growth of this public cyberinfrastructure resource is described and the domain science that it has enabled is reviewed.
Proceedings ArticleDOI

Chatbots and conversational agents: A bibliometric analysis

TL;DR: The results of the analysis found a potential research opportunity in chatbots due to the emergence of the deep learning technology, and several recommendations for future research are provided based on the results obtained.
Proceedings ArticleDOI

Iris: A Conversational Agent for Complex Tasks

TL;DR: This paper presents a new approach to designing conversational agents inspired by linguistic theory, where agents can execute complex requests interactively by combining commands through nested conversations in Iris, an agent that can perform open-ended data science tasks such as lexical analysis and predictive modeling.
Journal ArticleDOI

Understanding the brain

TL;DR: There is no single homunculus in the authors' brains that controls and manages all these distributed processes, and studies of the structural and functional organization of the brain have shown that this organ is, to a large extent, decentralized, and processes information in parallel in countless sensory and motor subsystems.
Related Papers (5)