Argumentation Support System Research Articles

Using semantic types to formalize and augment complex argumentative discourses

Argumentation support systems currently on the Web have yet to deliver their full potential to teams striving for informed sense and decision making. Today's widely used systems such as discussion forums do not support formalization and are poorly integrated in the environment of multidisciplinary teams that collaborate in data intensive and cognitive complex settings, such as those involving DNA analysis, marketing or drug testing research. Such teams use on a daily basis tools to collect big amounts of required data as well as sophisticated data mining tools to uncover patterns in the collected data. However, these tools do not interoperate with argumentation support systems. In this paper, we present an approach to support collaboration which exploits a range of semantic types to enable formalization of argumentative discourses. Semantic types also enable the integration of argumentation support systems with data mining services to further augment collaboration and decision making in the above teams. An evaluation of the approach shows that the platform enables stakeholders to make better, more informed and quicker decisions, by displaying the aggregated information according to their needs. The overall idea of our approach builds on the exploitation of the synergy between tools supporting machine and human intelligence.

Analyzing credibility of arguments in a web-based intelligent argumentation system for collective decision support based on K-means clustering algorithm

We developed an intelligent argumentation and collaborative decision support system which allows stakeholders to exchange arguments and captures their rationale. Arguments with lack of credibility in an argumentation tree may negatively affect decisions in a collaborative decision making process if they are not identified collectively by the group. To address this issue, we perform clustering analysis on an argumentation tree using K-means clustering algorithm on credibility factors of arguments such as degree of an argument, and collective determination of an argument. Arguments are classified into multiple groups: from highly credible to lack of credibility. It helps capture rationale of selection of the most favorable solution alternative by the system. It helps decision makers identify arguments with high credibility based on collective determination. We perform an empirical study of the method and its results indicate that it is effective in supporting collective decision making using the system.

Frame-based argumentation for group decision task generation and identification

One of the most important stages of group decision-making is the generation and identification of decision tasks. In this paper, we define a decision task with five elements: decision makers, decision executors, decision objectives, decision problems and decision constrains. Based on this distinction, we present a conceptual model for generation and identification of group decision tasks in an organization. In addition, we describe a prototype of a group argumentation support system (GASS) that applies frame-based information structure in electronic brainstorming (EBS) and argumentation to support group decision task generation and identification. Using four group performance indicators, the prototype was evaluated in a lab experiment to determine its effectiveness and efficiency.

A PLURALIST APPROACH TO VISUALISATION OF POLICY DISCOURSE

This paper proposes a pluralist approach to visualization of policy discourse. Argumentation support systems have been applied to political decision-making by visualizing the logical and linguistic structure of arguments. It is further needed that, in order to produce a better collective understanding of complex societal problems, such argumentation support systems have the capability of highlighting value conflicts based on different perspectives. The proposed methodology extracts those lines of arguments which are mutually exclusive but nevertheless each worth exploring. It has been applied to public arguments in a quasi-governmental committee. The paper reports on the outcome of the case study and discusses its implication for socio-technical systems. Language: ja

Computer-mediated communication: problems and potentials of argumentation support systems

Argumentation support systems have both advantages and disadvantages. For the individual, there is an increased power to express herself and to gain recognition and reward for the extra effort and frankness required, but at the cost of slowing down work, making the user constantly explain herself, and putting her statements at risk of being taken out of context. For the organisation, there is a gain in increased information sharing — the bane of current computer-mediated communication (CMC) systems — as the user is motivated to present relevant and convincing evidence to back up her statements, but at the cost of undermining `traditional' organisational structures and hierarchies.