Analysis of literature in scientific conferences and journals to identify and describe the evolution of trends is valuable for supporting the dissemination and distribution of knowledge in a large-scale decentralized research community. A trend is an increase in popularity, while a downtrend describes a decrease in popularity of a certain topic. The goal of this work is to extend our existing citation recommendation bot to provide temporal context information to the recommendations by time-series based trend analysis.
Thesis Type |
|
Student |
Nico Reinartz |
Status |
Finished |
Submitted in |
2024 |
Supervisor(s) |
Stefan Decker Sandra Geisler |
Advisor(s) |
Michal Slupczynski |
Contact |
slupczynski@dbis.rwth-aachen.de |
In our currently running project MILKI-PSY, we focus on multimodal immersive mentoring to facilitate Self Regulated Learning (SRL).
To support mentors with the tools they need to provide adaptive and personalized tutoring, a set of learning services was developed and is currently under development. These services utilize our flagship peer-to-peer community platform las2peer.
In order to cater their publications or events to the demands of the academic community, academic conference organizers must be informed of the most recent hot topics in research. Researchers seek to know where to focus their efforts in order to enhance their efficiency. However, doing a literature review and identifying popular study subjects is difficult without automated processes to structure and assess the research output. A time-series analysis of current patterns in research topics could provide insight into seasonality, trends, cyclicality, and unpredictability.
In previous work, we made use of the Social Bot Framework to implement an automated agent to provide academic citation recommendations to support students and researchers in their literature review process.
The goal of this thesis is to extend our existing automated literature review mechanism to provide trend and downtrend indicators.
If you are interested in this thesis, a related topic or have additional questions, please do not hesitate to send a message to slupczynski@dbis.rwth-aachen.de
Please apply with a meaningful CV and a recent transcript of your academic performance.
Potentially relevant literature:
- Tiago et al. 2018 “Visualizing Historical Patterns in Large Educational Datasets”
http://doi.org/10.4018/IJCICG.2018010103 - Moiseeva et al. 2020 “TRENDNERT: A Benchmark for Trend and Downtrend Detection in a Scientific Domain”
https://doi.org/10.1609/aaai.v34i05.6372 - Soumya et al. 2020 “A Novel Sequence Graph-Based Approach to Find Academic Research Trends”
http://doi.org/10.4018/IJWP.2020010104 - Lu et al. 2021 “Detecting research topic trends by author-defined keyword frequency”
http://doi.org/10.1016/j.ipm.2021.102594
- Web Technologies
- Java
- Python
- HTML/CSS
MILKI-PSY - Multimodales Immersives Lernen mit KI für Psychomotorische Fähigkeiten