AIDA-Bot 2.0: Enhancing Conversational Agents with Knowledge Graphs for Analysing the Research Landscape

Abstract

The crucial task of analysing the complex dynamics of the research landscape and uncovering the latest insights from the scientific literature is of paramount importance to researchers, governments, and commercial organizations. Springer Nature, one of the leading academic publishers worldwide, plays a significant role in this domain and regularly integrates and processes a variety of data sources to inform strategic decisions. Since exploring the resulting data is a challenging task, in 2021 we developed AIDA-Bot, a chatbot that addresses inquiries about the research landscape by utilising a large-scale knowledge graph of scholarly data. This paper presents the novel AIDA-Bot 2.0, which can both 1) support a set of predetermined question types by automatically translating them to formal queries on the knowledge graph, and 2) answer open questions by summarising information from relevant articles. We evaluated the performance of AIDA-Bot 2.0 through a comparative assessment against alternative architectures and an extensive user study. The results indicate that the novel features provide more accurate information and an excellent user experience.

DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization

“…SKGs support applications, like conversational or collaborative chatbots, that work with users to explore and navigate linked, scholarly information (Meloni et al 2021). To maximize the usability of the information encoded in SKGs, we use a large‐language model (LLM) to convert users' natural language questions into Cypher queries (an SQL‐inspired query language for graphs), which are expressed in a machine‐readable database language.…”