The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents;researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology.

/pdf/intelligent-agents-theory-and-practice-5dchj7p8pc.pdf

Intelligent Agents: Theory and Practice

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to almost all human activities and are key influencers of our behaviors. Our beliefs and perceptions of reality, and the choices we make, are largely conditioned on how others see and evaluate the world. For this reason, when we need to make a decision we often seek out the opinions of others. This is true not only for individuals but also for organizations. This book is a comprehensive introductory and survey text. It covers all important topics and the latest developments in the field with over 400 references. It is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular. Lecturers can readily use it in class for courses on natural language processing, social media analysis, text mining, and data mining. Lecture slides are also available online.

/pdf/sentiment-analysis-and-opinion-mining-8314pykwrf.pdf

Sentiment Analysis and Opinion Mining

The study of computational agents capable of rational behaviour has received a great deal of attention in recent years. Theoretical formalizations of such agents and their implementations have proceeded in parallel with little or no connection between them. Tkis paper explores a particular type of rational agent, a BeliefDesire-Intention (BDI) agent. The primary aim of this paper is to integrate (a) the theoretical foundations of BDI agents from both a quantitative decision-theoretic perspective and a symbolic reasoning perspective; (b) the implementations of BDI agents from an ideal theoretical perspective and a more practical perspective; and (c) the building of large-scale applications based on BDI agents. In particular, an air-trafflc management application will be described from both a theoretical and an implementation perspective.

/pdf/bdi-agents-from-theory-to-practice-4cue39s538.pdf

BDI Agents: From Theory to Practice

From the Publisher:
An agent is an entity with domain knowledge, goals and actions. Multi-agent systems are a set of agents which
interact in a common environment. Multi-agent systems deal with the construction of complex systems involving multiple agents and their coordination. A multi-agent system (MAS) is a distributed computing system with
autonomous interacting intelligent agents that coordinate their actions so as to achieve its goal(s) jointly or competitively.

Introduction to Multiagent Systems

We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.

Lexicon-based methods for sentiment analysis

When two people engage in a conversation, knowingly or unknowingly, they are playing a game. Players of such games have diverse objectives, or winning conditions: an applicant trying to convince her potential employer of her eligibility over that of a competitor, a prosecutor trying to convict a defendant, a politician trying to convince an electorate in a political debate, and so on. We argue that infinitary games offer a natural model for many structural characteristics of such conversations. We call such games message exchange games, and we compare them to existing game theoretic frameworks used in linguistics—for example, signaling games—and show that message exchange games are needed to handle non-cooperative conversation. In this paper, we concentrate on conversational games where players’ interests are opposed. We provide a taxonomy of conversations based on their winning conditions, and we investigate some essential features of winning conditions like consistency and what we call rhetorical cooperativity. We show that these features make our games decomposition sensitive, a property we define formally in the paper. We show that this property has far-reaching implications for the existence of winning strategies and their complexity. There is a class of winning conditions (decomposition invariant winning conditions) for which message exchange games are equivalent to Banach- Mazur games, which have been extensively studied and enjoy nice topological results. But decomposition sensitive goals are much more the norm and much more interesting linguistically and philosophically.

/pdf/message-exchange-games-in-strategic-contexts-25n1l6hvwe.pdf

Message Exchange Games in Strategic Contexts

We offer a semantics and pragmatics of the pluperfect in narrative discourse We examine in a formal model of implicature, how the reader's knowledge about the discourse, Gricean-maxims and causation contribute to the meaning of the pluperfect By placing the analysis in a theory where the interactions among these knowledge resources can be precisely computed, we overcome some problems with previous Reichenbachian approaches

/pdf/a-semantics-and-pragmatics-for-the-pluperfect-227e7m0l1a.pdf

A semantics and pragmatics for the pluperfect

A Gricean view of cognitive agents holds that agents are fully rational and adhere to the maxims of conversation that entail that speakers adopt shared intentions and fully aligned preferences– e.g. (Allen and Litman, 1987; Lochbaum, 1998). These assumptions are unwarranted in many conversational settings. In this paper we propose a different view and an annotation scheme for it. We propose a game theoretic approach to conversation. While we assume like Grice that conversational agents are rational, agents talk to maximize their expected utility (a measure that combines belief and preference). Preferences together with beliefs guide conversational actions as much as they guide non linguistic actions. Conversations are dynamic and extensive games, and they have an in principle unbounded number of possible moves and no mandatory stopping points— you can, in some sense, always say anything, and you can always continue a conversation. The moves for each player consist in making a discourse contribution, which we finitely characterize using discourse structure in the sense of (Asher and Lascarides, 2003). Such discourse structures consist of discourse units linked to each via discourse relations like Elaboration, QuestionAnswer-Pair (QAP) and Explanation. In addition these discourse relations serve to link one participant’s contribution to another; for instance, if one agent asks a question, another may respond with an answer, the two contributions then linked together by the relation QAP. Conversational participants are alternatively senders (S) or receivers of messages (R). S sends a signal s bearing in mind that receiver R has to figure out: (a) what is the message m(s)? What is S publicly committed to? (b) Is m(s) credible or not? (c) Given a status for m(s), what signal s′ should R send in return? R now becomes sender and S, now the receiver, goes through the calculation steps (a)-(c). We assume that at least part of the conventional meaning of the signal is determined prior to game play. In calculation (a), R must calculate using a form of generalized signaling game what are the public commitments that S has made—these include not only the fixed semantics but also the implicatures that introduce discourse relations between contributions. Sometimes these involve strategic considerations: for instance, is S actually replying to the question asked in the prior turn or is she engaged in some other discourse move? If she is answering the question, is this something that S cannot plausibly later deny? (Asher and Quinley, 2011) argue that a trust game format is the right one for computing optimal moves in task (c). (Traum and Allen, 1994) advocates a related view on which cooperativity is determined only by the social conventions guiding conversation, obligations that do not presuppose speakers adopt each other’s goals (Traum et al., 2008). For us, the social conventions that are foundational on Traum’s account are however themselves based on utility. Utility is also the basis for training agents to behave in a certain way through reinforcement learning for conversational agents (Frampton and Lemon, 2009).

Modelling Strategic Conversation: model, annotation design and corpus

The Right Frontier Constraint (RFC), as a constraint on the attachment of new constituents to an existing discourse structure, has important implications for the interpretation of anaphoric elements in discourse and for Machine Learning (ML) approaches to learning discourse structures. In this paper we provide strong empirical support for SDRT's version of RFC. The analysis of about 100 doubly annotated documents by five different naive annotators shows that SDRT's RFC is respected about 95% of the time. The qualitative analysis of presumed violations that we have performed shows that they are either click-errors or structural misconceptions.

Testing SDRT's Right Frontier

The aim of this paper is twofold: measuring the effect of discourse structure when assessing the overall opinion of a document and analyzing to what extent these effects depend on the corpus genre. Using Segmented Discourse Representation Theory as our formal framework, we propose several strategies to compute the overall rating. Our results show that discourse-based strategies lead to better scores in terms of accuracy and Pearson's correlation than state-of-the-art approaches.

/pdf/measuring-the-effect-of-discourse-structure-on-sentiment-41f1dn2cko.pdf

Nicholas Asher

Papers

Message Exchange Games in Strategic Contexts

A semantics and pragmatics for the pluperfect

Modelling Strategic Conversation: model, annotation design and corpus

Testing SDRT's Right Frontier

Measuring the effect of discourse structure on sentiment analysis