Argument-Based Decision Support for Recommender Systems (ASSURE)

用户生成的文本（如在线产品评论）中包含的论证性陈述可以显著地促进用户在面对大量选择时的决策过程，例如，在购买产品或在线预订酒店时。推荐系统的目标是通过推荐用户可能感兴趣的项目来缓解用户的决策问题，但目前还没有开发出支持或反对某个项目或其属性的合理论证的潜力。ASSURE项目的总体目标是利用在线评论中嵌入的论点来显著提高系统给出的推荐的质量和透明度，并为用户提供比目前情况更高水平的推荐过程交互式控制。该项目旨在在几个方面推进当前的技术水平：首先，我们将开发新的方法，从用户评论中发现的随意且通常特殊类型的文本中提取基于立场的论点。其次，我们将提取的参数与用户评分和其他与商品相关的数据结合在一个集成的用户和商品模型中，以提高推荐算法的有效性。该模型还将为开发新的技术提供基础，通过这些技术，用户可以交互式地探索、过滤或权衡不同的参数以及其他数据，以控制如何生成推荐。第三，我们将开发方法，为用户提供个性化的、基于论证的推荐项目解释。该项目的另一个重要成果将是一个前所未有的质量和规模的数据集，该数据集在基于立场的论证的不同层上进行了注释。这样的数据集是进一步研究论证和推荐的先决条件，并且适合用于构成优先级计划一部分的共享任务。该项目所追求的目标促成了DFG优先计划“健壮论证机”所描述的两个场景。它们解决了考虑场景，因为基于论证的建议和解释将支持用户在从非常大的选项集中选择项目时做出明智的决定。此外，我们还将开发用于综合场景的方法，因为单个参数和较大的参数集都必须以合适的个性化形式呈现给用户。所有开发都将伴随着受控的用户研究，以确保所开发的论据提取和推荐技术导致整个应用程序的高水平有效性和可用性。这些方法将以跨学科的方式开发，涉及计算语言学和人机交互领域，并将在现实世界的应用领域和集成的演示系统中进行验证。

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.