Skip to content. | Skip to navigation

Sections
Personal tools
You are here: Home Theses Citation recommendation bot

Contact

Prof. Dr. S. Decker
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

Citation recommendation bot

Thesis type
  • Bachelor
Status Running
Supervisor(s)
Advisor(s)

Current advances in recommender systems allow for context-specific suggestions of relevant literature based on various parameters. As a contextual help in writing scientific papers, a citation recommender system should aid the student by providing a personalized suggestion of publications to consider for the Related Work section of a publication. Hence, for this project, we want to employ mentoring bots to provide suggestions of relevant scientific publications to students to support their literature research.

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.

At our chair, we developed a Social Bot Framework, which allows for a model-driven construction and utilization of social bots in the domain of technology enhanced learning (TEL). Recent developments in TEL saw a rise in popularity of Distance Education (DE), which is characterized by the intense use of communication technologies and information systems to facilitate SRL. The main premise of SRL is for students to mostly work on their own accord supported by a Learning Management System (LMS). LMS (e.g. Moodle) is used to facilitate administration, delivery and tracking of educational courses. The application of social bots in LMS can be used to provide direct, context-specific feedback in SRL. With the latest enhancements, the bot is able to perform Moodle quizzes within a conversational channel (Slack or Rocket.Chat).

During their seminar courses, students are tasked with performing a full research on a topic given by a mentor. A major task of seminar classes is to present the research work in a format similar to scientific conferences. While the research topic stems from current faculty research, the student should explore the topic independently. However, students can encounter difficulties with determining whether the references are relevant and of high enough quality. Current advances in recommender systems allow for context-specific suggestions of relevant literature based on various parameters. As a contextual help in writing scientific papers, a citation recommender system should aid the student by providing a personalized suggestion of publications to consider for the Related Work section of a publication. Hence, for this project, we want to employ mentoring bots to provide suggestions of relevant scientific publications to students to support their literature research.

The goal of this thesis is to compare existing recommendation algorithms and extend our existing mentoring bot framework to provide relevant academic citations in the context of writing seminar papers.

Potentially relevant reading material:

 
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

Related projects

Document Actions