The inconsistency of the decision maker’s preferences may be measured as a number of violations of the transitivity rule. If the intensity of the preference is available, then the incosistency may be ...measured by measuring the inconsistency of each cycle of the preference graph. In the Potential Method, this may be accomplished by mesuring an angle (degree) between the preference flow and the column space of the incidence matrix.
In this article a random study is performed to determine the upper bound for admissible inconsistency. The degree distribution is recognized as the Gumbel distribution and the upper bound for admissible inconsistency measure is defined as a p-quantile (p = 0.05) of that distribution.
Conversational recommender systems discover users' preferences through dialog and make proper recommendations. Previous works fall into task-oriented and sociable conversational recommender systems. ...However, these works are not interpretable and sociable simultaneously. To address this problem, we propose a conversational recommender system with topic-related preference graph (CRTPG), consisting of a topic-related preference graph (TP-Graph) construction module, a key entity prediction module, and a dialog generation module. The TP-Graph recognizes the user's entity-level preference and keeps preference information for the recent topics. The key entity prediction module provides key entities as explicit content guidance for dialog generation based on TP-Graph. The dialog generation module generates appropriate responses based on the TP-Graph and knowledge related to key entities. TP-Graph and key entity help humans understand the precise information the system makes decisions based on, improving the interpretability of the system. We conduct automatic and human evaluations on the DuRecDial dataset. Experimental results show that CRTPG achieves state-of-the-art results on recommendation and dialog generation.
Music genres are useful for indexing, organizing, searching, and recommending songs and albums. Therefore, the automatic classification of music genres is an essential part of almost all kinds of ...music applications. Recent works focus on exploiting text, audio, or multi-modal information for genre classification, without considering the influence of the artists' and listeners' preference. However, intuitively, artists have their composing preferences, and listeners also have their music tastes. Both of them provide helpful hints to the music genre from different views, which are crucial to improve classification performance.
In this paper, we make use of both artist-music and listener-music preference relations to construct a heterogeneous preference graph. Then, we propose a novel graph-based neural network to automatically encode the global preference relations of the heterogeneous graph into artist and listener representations. We construct a graph to capture the correlations among genres and apply a graph convolutional network to learn genre representation from the correlation graph. Finally, we combine artist, listener, and genre representations for multi-label genre classification. Experimental results show that our model significantly outperforms the state-of-the-art methods on two public music genre classification datasets.
Label ranking is a complex prediction task where the goal is to map instances to a total order over a finite set of predefined labels. An interesting aspect of this problem is that it subsumes ...several supervised learning problems, such as multiclass prediction, multilabel classification, and hierarchical classification. Unsurprisingly, there exists a plethora of label ranking algorithms in the literature due, in part, to this versatile nature of the problem. In this paper, we survey these algorithms.
This paper examines an alternative method for analyzing a collection of Likert items in the multi-criteria decision framework. Likert items are compared in pairs and organized in a set of weighted ...digraphs which are aggregated according to the Potential Method rules. In combination with Factor Analysis this approach gives respondents’ preferences on the scale which approximates a measurable value function. As an application of
the proposed methodology, we examine a potential set of incentives and explore the degree to which they would be accepted by the industry. We use Potential Method to elicit firm’s preferences for given incentives and we seek to explain the difference in these preferences by the firm/market factors. Data is collected through a survey of 190 Croatian enterprises performed in 2002.
Freebase is a very large open knowledge database, which is generated in the form of community contributions, like Wikipedia. The idea of Freebase was first launched in 2000 by researchers in the ...field of web data, based on the concept of "knowledge web". Until 2010, Freebase was managed by Metaweb and the amount of data had reached 20 million topics. Appreciate the importance of this new approach, Freebase had been acquired by Google in June 2010 and continues to be developed so far. Based on the concepts of web data objects, information extraction is performed via Freebase APIs through HTTP protocol. This approach meets the requirements of common data query, however the downside is that it does not allow customizing the output for each user, or each application that needs to query on Freebase. In this paper, we propose a new approach to query Freebase data, which has the ability to customize the output for each user. Briefly, the system allows users to keep a desired graph which we call user's preference graph. Next, we use the APIs to query Freebase data. The difference here is that instead of returning the results to the user as the conventional Freebase API model, the system will use user's graph to adjust the query results, or continue to perform new queries. This process will be conducted repeated several times to achieve the target to search data in accordance with the wishes of the user.
Reaching to an agreement in meeting arrangements has always been a hard and cumbersome task, especially when there are many participants. An efficient approach to this problem is multi-agent systems. ...When we are designing a multi-agent system where agents are making decisions behalf of users we face another problem. How agents can model users' preferences? In this paper we are trying to cope with this problem. As we know analytical hierarchy process (AHP) technique is famous for its ability to determining preferences. In this paper an adaptive modeling technique based on AHP has been proposed.
Automated negotiation is important for carrying out flexible transactions. Agents that take part in automated negotiation need to have a concise representation of their user’s preferences and should ...be able to reason on these preferences effectively. We develop an automated negotiation platform wherein consumer agents negotiate with producer agents about services. A consumer agent represents its user’s preferences in a compact way using a CP-net, which is a structure that allows users to order their preferences based on the different value combinations of attributes. Acquiring user’s preferences in a compact way is crucial since it significantly decreases the number of questions to be asked to the user by the consumer agent. We design strategies for consumer agents to reason on and negotiate effectively with the preference graph induced from a CP-net. These strategies are designed to generate deals that are acceptable by the provider and the consumer. We compare our proposed strategies in terms of how well and how quickly they can find desirable deals for the consumer.
Mathematical model of a goal-oriented thinking with feedback is described. Basic notions: decision graph, feed-back hierarchy and self-duality are introduced and explained. A source of the conflict ...in our approach is the ignorance about the importance of decision maker's goals. In contrast to Shar, Simonson & Tversky 4 and Deutsch 2 conflict resolution is modeled as a problem of finding a fixed point of a self-assessment operator, i.e. without adding or removing any decision element from decision hierarchy.