K. Robert Lai

Modeling Agent Negotiation Via Fuzzy Constraints in E-Business

In e‐business, disputes between two or more parties arise for various reasons and involve different issues. Thus, resolution of these disputes frequently relies on some form of negotiation. This article presents a general problem‐solving framework for modeling multi‐issue multilateral agent negotiation using fuzzy constraints in e‐business. Fuzzy constraints are thus used not only to define each agents demands involving human concepts, but also to represent the relationships among agents. A concession strategy, based on fuzzy constraint‐based problem‐solving, is proposed to relax demands, and a trade‐off strategy is presented to evaluate existing alternatives. This approach provides a systematic method for reaching an agreement that benefits all agents with a high satisfaction degree of constraints. Meanwhile, by applying the method, agents can move toward an agreement more quickly, because their search focuses only on the feasible solution space. An example application to negotiate an insurance policy among agents is provided to demonstrate the usefulness and effectiveness of the proposed framework.

A hybrid system by evolving case-based reasoning with genetic algorithm in wholesaler's returning book forecasting

A hybrid system by evolving a Case-Based Reasoning (CBR) system with a Genetic Algorithm (GA) is developed for wholesalers returning book forecasting. For a new book, key factors, such as the grade of the author, the grade of publisher, hot or slow season of publication date, sale volumes for the first 3 months and the returning rate, have been identified and applied as the key features to calculate the similarity coefficient of a new release book and to retrieve similar book from the reference cases to justify if the new book is a slow-selling or selling book. The case base of this research is acquired from a book wholesaler in Taiwan, and it is applied by the hybrid system to forecast returning books. The results of the prediction of the hybrid system were compared with the results of a back propagation neural network (BPNN), a conventional CBR, and a multiple-regression analysis method. The experimental results show that the GA/CBR is more accurate and efficient when being applied to the forecast of the returning books than other methods.

Building Chinese Affective Resources in Valence-Arousal Dimensions

An increasing amount of research has recently focused on representing affective states as continuous numerical values on multiple dimensions, such as the valence-arousal (VA) space. Compared to the categorical approach that represents affective states as several classes (e.g., positive and negative), the dimensional approach can provide more finegrained sentiment analysis. However, affective resources with valence-arousal ratings are still very rare, especially for the Chinese language. Therefore, this study builds 1) an affective lexicon called Chinese valence-arousal words (CVAW) containing 1,653 words, and 2) an affective corpus called Chinese valencearousal text (CVAT) containing 2,009 sentences extracted from web texts. To improve the annotation quality, a corpus cleanup procedure is used to remove outlier ratings and improper texts. Experiments using CVAW words to predict the VA ratings of the CVAT corpus show results comparable to those obtained using English affective resources.

Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model

Dimensional sentiment analysis aims to recognize continuous numerical values in multiple dimensions such as the valencearousal (VA) space. Compared to the categorical approach that focuses on sentiment classification such as binary classification (i.e., positive and negative), the dimensional approach can provide more fine-grained sentiment analysis. This study proposes a regional CNN-LSTM model consisting of two parts: regional CNN and LSTM to predict the VA ratings of texts. Unlike a conventional CNN which considers a whole text as input, the proposed regional CNN uses an individual sentence as a region, dividing an input text into several regions such that the useful affective information in each region can be extracted and weighted according to their contribution to the VA prediction. Such regional information is sequentially integrated across regions using LSTM for VA prediction. By combining the regional CNN and LSTM, both local (regional) information within sentences and long-distance dependency across sentences can be considered in the prediction process. Experimental results show that the proposed method outperforms lexicon-based, regression-based, and NN-based methods proposed in previous studies.

Predicting Valence-Arousal Ratings of Words Using a Weighted Graph Method

Compared to the categorical approach that represents affective states as several discrete classes (e.g., positive and negative), the dimensional approach represents affective states as continuous numerical values on multiple dimensions, such as the valence-arousal (VA) space, thus allowing for more fine-grained sentiment analysis. In building dimensional sentiment applications, affective lexicons with valence-arousal ratings are useful resources but are still very rare. Therefore, this study proposes a weighted graph model that considers both the relations of multiple nodes and their similarities as weights to automatically determine the VA ratings of affective words. Experiments on both English and Chinese affective lexicons show that the proposed method yielded a smaller error rate on VA prediction than the linear regression, kernel method, and pagerank algorithm used in previous studies.

Fuzzy constraint-based agent negotiation

Conflicts between two or more parties arise for various reasons and perspectives. Thus, resolution of conflicts frequently relies on some form of negotiation. This paper presents a general problem-solving framework for modeling multi-issue multilateral negotiation using fuzzy constraints. Agent negotiation is formulated as a distributed fuzzy constraint satisfaction problem (DFCSP). Fuzzy constrains are thus used to naturally represent each agent’s desires involving imprecision and human conceptualization, particularly when lexical imprecision and subjective matters are concerned. On the other hand, based on fuzzy constraint-based problem-solving, our approach enables an agent not only to systematically relax fuzzy constraints to generate a proposal, but also to employ fuzzy similarity to select the alternative that is subject to its acceptability by the opponents. This task of problem-solving is to reach an agreement that benefits all agents with a high satisfaction degree of fuzzy constraints, and move towards the deal more quickly since their search focuses only on the feasible solution space. An application to multilateral negotiation of a travel planning is provided to demonstrate the usefulness and effectiveness of our framework.

Learning opponent's beliefs via fuzzy constraint-directed approach to make effective agent negotiation

This work presents a general framework of agent negotiation with opponent learning via fuzzy constraint-directed approach. The fuzzy constraint-directed approach involves the fuzzy probability constraint and the fuzzy instance reasoning. The proposed approach via fuzzy probability constraint can not only cluster the opponent’s information in negotiation process as proximate regularities to improve the convergence of behavior patterns, but also eliminate the noisy hypotheses or beliefs to enhance the effectiveness on beliefs learning. By using fuzzy instance method, our approach can reuse the prior opponent knowledge to speed up the problem-solving, and reason the proximate regularities to acquire desirable results on predicting opponent behavior. In addition, the proposed interaction method enables the agent to make a concession dynamically based on expected objectives. Moreover, experimental results suggest that the proposed framework allows an agent to achieve a higher reward, a fairer deal, or a smaller cost of negotiation.

Agent-based fuzzy constraint-directed negotiation mechanism for distributed job shop scheduling

This paper presents an agent-based fuzzy constraint-directed negotiation (AFCN) mechanism to solve distributed job shop scheduling problems (JSSPs). The scheduling problem is modelled as a set of fuzzy constraint satisfaction problems (FCSPs), interlinked by inter-agent constraints. Each FCSP represents the perspective of the participants and is governed by autonomous agents. The novelty of the proposed AFCN is to bring the concept of a fuzzy membership function to represent the imprecise preferences of task start time for job and resource agents. This added information sharing is crucial for the effectiveness of distributed coordination. It not only can speed up the convergence, but also enforce a global consistency through iterative exchange of offers and counter-offers. The AFCN mechanism can also flexibly adopt different negotiation strategies, such as competitive, win-win, and collaborative strategies, for different production environments. The experimental results demonstrate that the proposed model can provide not only high-quality and cost-effective job shop scheduling (i.e., comparable to that of centralized methods) but also superior performance in terms of the makespan and average flow time compared with other negotiation models for agent-based manufacturing scheduling. As a result, the proposed AFCN mechanism is flexible and useful for distributed manufacturing scheduling with unforeseen disturbances. Display Omitted Agent-based fuzzy constraint-directed negotiation (AFCN) mechanism is proposed.To achieve autonomous cooperation for distributed job shop scheduling.AFCN mechanism is flexible to incorporate different negotiation strategies.AFCN mechanism outperforms both auction-based negotiation and the contract net protocol.

Community-Based Weighted Graph Model for Valence-Arousal Prediction of Affective Words

Compared to the categorical approach that represents affective states as several discrete classes (e.g., positive and negative), the dimensional approach represents affective states as continuous numerical values in multiple dimensions, such as the valence-arousal (VA) space, thus allowing for more fine-grained sentiment analysis. In building dimensional sentiment applications, affective lexicons with VA ratings are useful resources but are still very rare. Several semi-supervised methods such as the kernel method, linear regression, and the pagerank algorithm have been investigated to automatically determine the VA ratings of affective words from a set of semantically similar seed words. These methods suffer from two major limitations. First, they apply an equal weight to all seeds similar to an unseen word in predicting its VA ratings. Second, even similar seeds may have quite different ratings (or an inverse polarity) of valence/arousal to the unseen word, thus reducing prediction performance. To overcome these limitations, this study proposes a community-based weighted graph model that can select seeds which are both similar to and have similar ratings (or the same polarity) with each unseen word to form a community (subgraph) so that its VA ratings can be estimated from such high-quality seeds using a weighted propagation scheme. That is, seeds more similar to unseen words contribute more to the estimation process. Experimental results show that the proposed method yields better prediction performance for both English and Chinese datasets.

Negotiation based adaptive learning sequences

This study proposes a negotiation-based approach to combine the notion of adaptivity (system-controlled adaptation) and adaptability (user-controlled adaptation) for an adaptive learning system. The system suggests adaptations and the student also submits his/her adaptation preference. When the student preference opposes the system suggestion, the student then negotiates with the system to reach an agreement of adaptation. A negotiation-based adaptive learning system (NALS) is implemented to support the generation of personalized adaptive learning sequences by system negotiations with students regarding assessments of learning performance (i.e. negotiated open student model) of the current content and choices of the next learning content (i.e. negotiation of adaptation). Students require two metacognitions in deciding adaptive learning sequences: self-assessment for evaluating their understanding of the current content and regulation for choosing appropriate learning content. Negotiated open student model are used for assist student self-assessment and negotiation of adaptation are used for assist student regulation of content choices. An experiment was conducted to compare a system-controlled adaptive learning system (SALS, adaptivity), a user-controlled adaptive learning system (UALS, adaptability), and a NALS. The results revealed that NALS promoted better metacognitions in student calibration (i.e. self-assessment) accuracy and learning content choices (i.e. regulation). Preliminary evidences also showed that NALS promoted better student performance in a delay test. The results further suggested that students with poor calibration accuracy and inappropriate content choices were not suitable to use UALS and were suitable to use SALS. The NALS can also be used for training students to make appropriate adaptation for learning. A negotiation-based adaptive learning system (NALS) combines adaptivity and adaptability.The NALS system enhanced student calibration (self-assessment) accuracy and learning content choices (regulation).The NALS system promoted better student performance in a delay test.The NALS system can be used for training students to make suitable learning adaptation.