We consider classification of email messages as to whether or not they contain certain “email acts”, such as a request or a commitment. We show that exploiting the sequential correlation among email messages in the same thread can improve email-act classification. More specifically, we describe a new textclassification algorithm based on a dependency-network based collective classification method, in which the local classifiers are maximum entropy models based on words and certain relational features. We show that statistically significant improvements over a bag-of-words baseline classifier can be obtained for some, but not all, email-act classes. Performance improvement obtained by collective classification is appears to be consistent across email acts suggested by prior speech-act theory.

Currently, standards for web services are being developed via three different initiatives (W3C, Semantic web services and ebXML). To the best of our knowledge, no theoretical perspectives underlie these standardization efforts. Without the benefit of a strong theoretical basis, the results, within and across these initiatives, have remained piecemeal. We suggest ‘Language-Action Theories’ as a plausible perspective that can effectively define, assess and refine web services standards. In this paper, we first investigate the existing initiatives to identify commonalities that point to theories of ‘Language-Action’ as an appropriate theoretical basis for web services standards. Next, we adapt work from these theories to develop a comprehensive reference framework for understanding web services standards. Finally, we use this reference framework to assess the three initiatives, and analyze the findings to provide insights for future development and refinement of web services standards.

Natural language that people use in electronic communication is far from perfect, due to the narrow channel. This also applies to electronic negotiation. We analyze characteristics of the language data obtained from electronic negotiation. We introduce a novel procedure for extracting and building a lexicon from raw noisy data. The data belong to a closed domain, which allows us to perform domaindependent word-sense disambiguation. The procedure itself is domain-independent and should work with data from various text collections. We present the results of an application of our procedure to a text corpus collected by an electronic negotiation support system.

genehmigte

Abstract. Negotiation Support Systems (NSSs) offer a multidimensional support of negotiations through the internet. Different kind of conflicts – apart from the initial conflict – can occur during this process. This paper will give an overview of the current state-of-the-art in managing electronic negotiations with the help of NSSs and it introduces an advanced conflict management concept to resolve escalated conflicts during the negotiation.