Argument-Based Decision Support for Recommender Systems (ASSURE)

• Applicants: Professor Dr.-Ing. Torsten Zesch; Professor Dr.-Ing. Jürgen Ziegler
• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing ; General and Comparative Linguistics, Experimental Linguistics, Typology, Non-European Languages
• Term: from 2017 to 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 375363654

Argumentative statements contained in user-generated texts such as online product reviews can significantly facilitate a user's decision process when faced with a large number of alternatives, for instance, when buying a product or booking a hotel online. Recommender systems aim at alleviating the user's decision problem by suggesting items the user is likely interested in, but do currently not exploit the potential of reasoned arguments given for or against a certain item or its properties. The overall objective of ASSURE project is to make use of arguments embedded in online reviews to significantly improve the quality and transparency of recommendations given by the system, and to provide users with a much higher level of interactive control over the recommendation process than is currently the case.The project aims at advancing the state of the art in several respects: Firstly, we will develop novel methods for extracting stance-based arguments from the casual and often idiosyncratic type of text found in user reviews. Secondly, we will combine the extracted arguments with user ratings and other item-related data in an integrated user and item model to improve the effectiveness of recommender algorithms. This model will also provide a basis for developing novel techniques through which users can interactively explore, filter, or weight different arguments, as well as other data, to control how recommendations are generated. Thirdly, we will develop methods for providing users with personalized, argument-based explanations of the items recommended. A further important outcome of the project will be a dataset of unprecedented quality and size that is annotated on different layers regarding stance-based argumentation. Such a dataset is a prerequisite for further research on argumentation and recommendation, and will be suited for use in shared tasks that form part of the priority program. The objectives pursued in this project contribute to two of the scenarios described for the DFG Priority Program "Robust Argumentation Machines". They address the deliberation scenario since the argument-based recommendations and explanations will support users in making informed decisions when selecting items from very large sets of options. In addition, we will also develop methods for the synthesis scenario because both single arguments and larger sets of arguments will have to be presented to users in suitable, personalized form. All developments will be accompanied by controlled user studies to ensure that the argument extraction and recommender techniques developed lead to a high level of effectiveness and usability of the overall application. The methods will be developed in a strongly interdisciplinary approach involving the areas of Computational Linguistics and Human-Computer Interaction and will be validated in a real-world application domain and with an integrated demonstrator system.

• DFG Programme: Priority Programmes
• Subproject of: SPP 1999: Robust Argumentation Machines (RATIO)