Loading...
Paper Number
2881
Paper Type
Complete
Abstract
We present a framework for ontology-based knowledge synthesis from research articles to support researchers in conducting literature reviews and gaining comprehensive insights into the state of the Information Systems discipline. Building on calls for an academic knowledge infrastructure, we performed a design science research project to (1) develop a conceptual framework incorporating the semantic annotation of research articles based on a domain ontology, (2) provide a process model, a data model, and an operations model that can guide the development of tools to support literature reviews, and (3) evaluate this framework within a proof-of-concept implementation. We evaluated the prototype against manually labeled abstracts and large language model- based tools. We further tested its practical application in semi-automated literature reviews. The results indicate that the proposed framework can support researchers in knowledge extraction and synthesis when analyzing large volumes of articles while saving time and effort.
Recommended Citation
Huettemann, Sebastian; Mueller, Roland; Larsen, Kai; and Dinter, Barbara, "A Framework for Ontology-Based Knowledge Synthesis from Research Articles" (2024). ICIS 2024 Proceedings. 3.
https://aisel.aisnet.org/icis2024/lit_review/lit_review/3
A Framework for Ontology-Based Knowledge Synthesis from Research Articles
We present a framework for ontology-based knowledge synthesis from research articles to support researchers in conducting literature reviews and gaining comprehensive insights into the state of the Information Systems discipline. Building on calls for an academic knowledge infrastructure, we performed a design science research project to (1) develop a conceptual framework incorporating the semantic annotation of research articles based on a domain ontology, (2) provide a process model, a data model, and an operations model that can guide the development of tools to support literature reviews, and (3) evaluate this framework within a proof-of-concept implementation. We evaluated the prototype against manually labeled abstracts and large language model- based tools. We further tested its practical application in semi-automated literature reviews. The results indicate that the proposed framework can support researchers in knowledge extraction and synthesis when analyzing large volumes of articles while saving time and effort.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
25-LitReviews