Michal Ptaszynski

CAO: A Fully Automatic Emoticon Analysis System Based on Theory of Kinesics

This paper presents CAO, a system for affect analysis of emoticons in Japanese online communication. Emoticons are strings of symbols widely used in text-based online communication to convey user emotions. The presented system extracts emoticons from input and determines the specific emotion types they express with a three-step procedure. First, it matches the extracted emoticons to a predetermined raw emoticon database. The database contains over 10,000 emoticon samples extracted from the Web and annotated automatically. The emoticons for which emotion types could not be determined using only this database, are automatically divided into semantic areas representing “mouths” or “eyes,” based on the idea of kinemes from the theory of kinesics. The areas are automatically annotated according to their co-occurrence in the database. The annotation is first based on the eye-mouth-eye triplet, and if no such triplet is found, all semantic areas are estimated separately. This provides hints about potential groups of expressed emotions, giving the system coverage exceeding 3 million possibilities. The evaluation, performed on both training and test sets, confirmed the systems capability to sufficiently detect and extract any emoticon, analyze its semantic structure, and estimate the potential emotion types expressed. The system achieved nearly ideal scores, outperforming existing emoticon analysis systems.

Humor Prevails! - Implementing a Joke Generator into a Conversational System

This paper contains the results of evaluation experiments conducted to investigate if implementation of a pun generator into a non-task oriented talking system improves the latters performance. We constructed a simple joking conversational system and conducted one user evaluation experiment and two third person evaluation experiments. The results showed that humor does have a positive influence on the dialogue between humans and computers. The implications of this fact and problems that occurred during the research are discussed. We also propose how they can be solved in the future.

Automatically annotating a five-billion-word corpus of Japanese blogs for sentiment and affect analysis

This paper presents our research on automatic annotation of a five-billion-word corpus of Japanese blogs with information on affect and sentiment. We first perform a study in emotion blog corpora to discover that there has been no large scale emotion corpus available for the Japanese language. We choose the largest blog corpus for the language and annotate it with the use of two systems for affect analysis: ML-Ask for word- and sentence-level affect analysis and CAO for detailed analysis of emoticons. The annotated information includes affective features like sentence subjectivity (emotive/non-emotive) or emotion classes (joy, sadness, etc.), useful in affect analysis. The annotations are also generalized on a two-dimensional model of affect to obtain information on sentence valence (positive/negative), useful in sentiment analysis. The annotations are evaluated in several ways. Firstly, on a test set of a thousand sentences extracted randomly and evaluated by over forty respondents. Secondly, the statistics of annotations are compared to other existing emotion blog corpora. Finally, the corpus is applied in several tasks, such as generation of emotion object ontology or retrieval of emotional and moral consequences of actions.

Affect analysis in context of characters in narratives

This paper presents our research in text-based affect analysis (AA) of narratives. AA represents a task of estimating or recognizing emotions elicited by a certain semiotic modality. In text-based AA the modality in focus is the textual representation of language. In this research we study particularly one type of language realization, namely narratives (e.g., stories, fairy tales, etc.). Affect analysis within the context of narratives is a challenging task because narratives are created of different kinds of sentences (descriptions, dialogs, etc.). Moreover, different characters become subjects of different emotional expressions in different parts of narratives. In this research we address the problem of person/character related affect recognition in narratives. We propose a method for emotion subject extraction from a sentence based on analysis of anaphoric expressions and compare two methods for affect analysis. We evaluate the system and discuss its possible future improvements.

Contextual affect analysis: a system for verification of emotion appropriateness supported with Contextual Valence Shifters

This paper presents a novel method for estimating speakers affective states based on two contextual features: valence shifters and appropriateness. Firstly, a system for affect analysis is used to recognise specific types of emotions. We improve the baseline system with the analysis of Contextual Valence Shifters (CVS), which determine the semantic orientation of emotive expressions. Secondly, a web mining technique is used to verify the appropriateness of the recognised emotions for the particular context. Verification of contextual appropriateness of emotions is the next step towards implementation of Emotional Intelligence Framework in machines. The proposed method is evaluated using two conversational agents.

Straight thinking straight from the net - on the web-based intelligent talking toy development

This paper introduces an early stage of a smart toy development project which combines several techniques to achieve a level of conversational skills and knowledge higher than currently available robots for children. We describe our ideas and achievements for three modules which we treat as the most important - topic unlimited talking engine, emotions recognizer and the moral behavior analyzer. We will also mention our novel evaluation method for freely speaking agents and possibilities of adding another module - an automatic joke generator.

Serious processing for frivolous purpose: a chatbot using web-mining supported affect analysis and pun generation

By our demonstration we want to introduce our achievements in combining different purpose algorithms to build a chatbot which is able to keep a conversation on any topic. It uses snippets of Internet search results to stay within a context, Nakamuras Emotion Dictionary to detect an emotional load existence and categorization of a textual utterance and a causal consequences retrieval algorithm when emotive features are not found. It is also able to detect a possibility to make a pun by analyzing the input sentence and create one if timing is adequate.

Humorized Computational Intelligence towards User-Adapted Systems with a Sense of Humor

This paper investigates the role of humor in non-task oriented (topic restriction free) human-computer dialogue, as well as the correlation between humor and emotions elicited by it in users. A joke-telling conversational system, constructed for the needs of this research, was evaluated by the users as better and more human-like than a baseline system without humor. Automatic emotive evaluation with the usage of an emotiveness analysis system showed that the system with humor elicited more emotions than the other one, and most of them (almost 80%) were positive. This shows that the presence of humor makes computers easier to familiarize with and simply makes users feel better. Therefore, humor should be taken into consideration in research on user-friendly applications, as it enhances the interaction between user and system. The results are discussed and our concept of a user-adapted humor-equipped system is presented.

Affect as Information about Users' Attitudes to Conversational Agents

This paper presents a novel method for automatic evaluation of conversational agents. In the method, information about userspsila attitudes and sentiments to conversational agents and their performance are achieved by analyzing their general emotional engagement in the conversation and specific affective states, and interpreting them using psychological reasoning of affect-as-information. In the evaluation experiment the userspsila attitudes to two Japanese-speaking conversational agents were checked simultaneously in a survey and using a system constructed on the proposed method. The results returned by the system revealed similar tendencies as the survey. Therefore the method is applicable as a mean of evaluation for Japanese-speaking conversational agents.

Detecting Emotive Sentences with Pattern-based Language Modelling

Abstract This paper presents our research in detection of emotive (emotionally loaded) sentences. The task is defined as a text classification problem with an assumption that emotive sentences stand out both lexically and grammatically. The assumption is verified exper- imentally. The experiment is based on n-grams as well as more sophisticated patterns with disjointed elements. To deal with the sophisticated patterns a novel language modelling algorithm based on the idea of language combinatorics is applied. The results of experiments are explained with the standard means of Precision, Recall and balanced F-score. The algorithm also provides a refined list of most frequent sophisticated patterns typical for both emotive and non-emotive context.