Providing Arguments in Discussions on the Basis of the Prediction of Human Argumentative Behavior

Abstract

Argumentative discussion is a highly demanding task. In order to help people in such discussions, this article provides an innovative methodology for developing agents that can support people in argumentative discussions by proposing possible arguments. By gathering and analyzing human argumentative behavior from more than 1000 human study participants, we show that the prediction of human argumentative behavior using Machine Learning (ML) is possible and useful in designing argument provision agents. This paper first demonstrates that ML techniques can achieve up to 76% accuracy when predicting people’s top three argument choices given a partial discussion. We further show that well-established Argumentation Theory is not a good predictor of people’s choice of arguments. Then, we present 9 argument provision agents, which we empirically evaluate using hundreds of human study participants. We show that the Predictive and Relevance-Based Heuristic agent (PRH), which uses ML prediction with a heuristic that estimates the relevance of possible arguments to the current state of the discussion, results in significantly higher levels of satisfaction among study participants compared with the other evaluated agents. These other agents propose arguments based on Argumentation Theory; propose predicted arguments without the heuristics or with only the heuristics; or use Transfer Learning methods. Our findings also show that people use the PRH agents proposed arguments significantly more often than those proposed by the other agents.

Show Me Your Evidence - an Automatic Method for Context Dependent Evidence Detection

“…Other works focused on specific domains such as evidence-based legal documents (Mochales Palau and Moens, 2011;Ashley and Walker, 2013), online debates (Cabrio and Villata, 2012;Boltužić andŠnajder, 2014), and product reviews (Villalba and Saint-Dizier, 2012;Yessenalina et al, 2010). In addition, some works based on machinelearning techniques, used the same topic in training and testing (Rosenfeld and Kraus, 2015;Boltužić anď Snajder, 2014), relying on features from the topic itself in identifying arguments. In contrast, here, we focus on detecting an essential constituent of an argumentthe evidence -rather then detecting whole arguments, or detecting other argument parts like claims Lippi and Torroni, 2015).…”

Updating Probabilistic Epistemic States in Persuasion Dialogues

“…There are proposals for modelling the likelihood of the moves that an opposing agent might make (e.g. [16,6,7,17]). Note, however, that none of the above proposals consider the beliefs of the opposing agent.…”

Towards a framework for computational persuasion with applications in behaviour change1

“…In a study of argumentation dialogues, Rosenfeld and Kraus [129] undertook an experiment in order to develop a machine learning-based approach to predict the next move a participant would make in a dialogue. This work was further extended in [130,131].…”

“…This work was further extended in [130,131]. The machine learning models were trained on data that incorporated the sequences of arguments in a dialogue that the participants accept.…”