Search

In this paper, we present a Deep Learning-based system for the support of information triaging on Twitter during emergency situations, such as disasters, or other influential events, such as political elections. The system is based on the assumption that a different type of information is required right after the event and some time after the event occurs. In a preliminary study, we analyze the language behavior of Twitter users during two kinds of influential events, namely, natural disasters and political elections. In the study, we analyze the credibility of information included by users in tweets in the above-mentioned situations, by classifying the information into two kinds: Primary Information (first-hand reports) and Secondary Information (second-hand reports, retweets, etc.). We also perform sentiment analysis of the data to check user attitudes toward the occurring events. Next, we present the structure of the system and compare a number of classifiers, including the proposed one based on Convolutional Neural Networks. Finally, we validate the system by performing an in-depth analysis of information obtained after a number of additional events, including an eruption of a Japanese volcano Ontake on 27 September 2014, as well as heavy rains and typhoons that occurred in 2020. We confirm that the methods works sufficiently well even when trained on data from nearly 10 years ago, which strongly suggests that the model is well-generalized and sufficiently grasps important aspects of each type of classified information.

The article deals with the issue of quality improvement of a gear transmission by optimizing its geometry with the use of genetic algorithms. The optimization method is focused on increasing productivity and efficiency of the pump and reducing its pulsation. The best results are tested on mathematical model and automatically modelled in 3D be means of PTC Creo Software. The developed solution proved to be an effective tool in the search for better results, which greatly improved parameters of pump especially reduced flow pulsation.

Cyberbullying, or humiliating people using the Internet, has existed almost since the beginning of Internet communication.The relatively recent introduction of smartphones and tablet computers has caused cyberbullying to evolve into a serious social problem. In Japan, members of a parent-teacher association (PTA)attempted to address the problem by scanning the Internet for cyber bullying entries. To help these PTA members and other interested parties confront this difficult task we propose a novel method for automatic detection of malicious Internet content. This method is based on a combinatorial approach resembling brute-force search algorithms, but applied in language classification. The method extracts sophisticated patterns from sentences and uses them in classification. The experiments performed on actual cyberbullying data reveal an advantage of our method vis-à-visprevious methods. Next, we implemented the method into an application for Android smartphones to automatically detect possible harmful content in messages. The method performed well in the Android environment, but still needs to be optimized for time efficiency in order to be used in practice

5.1 The socialized conversational agent algorithm With already started attempts of combining the systems described above, we decided to combine them all and make the next step on the path to a naturally chatting agent. As the first step we decided to implement the following algorithm (see Figure 7): first, the emotive recogniser tries to categorize the emotion included inside the user's utterance. Here

Accessibility and economic sustainability of public bus services (PBS) have been in a continuous decline in Japan’s countryside. Rural cities also suffer from population transformation toward industrial centers experiencing rapid economic growth. In the present study, we reviewed the current demand status of PBS in Kitami, a rural city in Japan that hosts a national university. The investigation was performed by examining students’ daily lives using a survey to collect data representing a portion of the population. The objective was to predict the change in demand rate for PBS concerning the necessities of everyday life from the perspective of university students as potential users of PBS. Intuitively, decision-makers at every level display a distinct prejudice toward alternatives that intend to change the long-lasting status quo, hence in the question sequence, a two-step verification probe was used to reveal a person’s actual perceived opinion. Accordingly, the respondents’ initial demand rate for PBS was around 60%, however, this score increased to 71% in the secondary confirmation. Afterward, using machine learning-based prediction methods, we could predict this demand at over 90% of F-measure, with the most reliable and stable prediction method reaching 80% by other daily life indicators’ weight. Finally, we supplied thorough evidence for our approach’s usability by collecting and processing the data’s right set regarding this study’s objective. This method’s highlighted outcomes would help to reduce the local governments’ and relevant initiatives’ adaptability time to demands and improve decision-making flexibility.

In this paper we present our research devoted to the development of Natural Language Processing technologies for the Ainu language, a critically endangered language isolate spoken by the Ainu people, the native inhabitants of northern parts of the Japanese archipelago. In particular, we focused on improving the existing tools for transcription normalization, word segmentation (tokenization) and part-of-speech tagging. In the experiments we applied two Ainu language dictionaries from different domains (literary and colloquial) and created a new data set by combining them. The experiments confirmed the positive effect of these modifications on the overall performance of the tools, especially with objective samples unrelated to the training data. We also discuss further improvements obtained by applying corpus-driven language models to the problem of word segmentation and using a state-of-the-art tool for training part-of-speech taggers.

E-mail is a communication tool widely used by people of all ages on the Internet today, often in business and formal situations, especially in Japan. Moreover, Japanese E-mail communication has a set of specific rules taught using specialized guidebooks. E-mail literacy education for many Japanese students is typically provided in a traditional, yet inefficient lecture-based way. We propose a system to support Japanese students in writing E-mails to superiors (teachers, job hunting representatives, etc.). We firstly make an investigation into the importance of formal E-mails in Japan, and what is needed to successfully write a formal E-mail. Next, we develop the system with accordance to those rules. Finally, we evaluated the system twofold. The results, although performed on a small number of samples, were generally positive, and clearly indicated additional ways to improve the system.

In this chapter, the authors present a method for automatic detection of malicious internet contents, based on a combinatorial approach resembling brute force search algorithms, with application to language classification. The method automatically extracts sophisticated patterns from sentences and applies them in classification. The experiments performed on actual cyberbullying data showed advantage of this method to previous methods, including the one described in Chapter 4. Pros and cons of this method when compared to previous ones are also discussed in this chapter.

In this paper, we propose a dialogue-based navigation system for narrow areas (e.g., buildings, etc.). In particular, we develop Campus Navigation Partner System (CNPS), intended for the use by freshmen (first-year students) who are likely to get lost in the new environment on the university campus (with the campus of Kitami Institute of Technology set as the experimental environment). The CNPS operates on a smartphone and has the functions of facility navigation and indoor information presentation. Indoor environment navigation is typically a problematic task because GNSS (Global Navigation Satellite System) signals cannot be received with sufficient accuracy within concrete walls. Therefore, we utilized natural language dialogue as a navigation method that guides the users within the facility using navigation messages and images. To investigate the effectiveness of the constructed system, we conducted practical experiments with freshmen and senior students of the university and evaluated the performance of the navigation functionality. Moreover, we investigated the general impressions of the system which we evaluated separately with both freshmen and senior students to clarify the differences in evaluation viewpoints between freshmen and users experienced in the campus environment (graduate students, etc.).

Irony and sarcasm detection is considered a complex task in Natural Language Processing. This paper set out to explore the sarcasm and irony on Twitter, using Machine Learning and Feature Engineering techniques. First we review and clarify the definition of irony and sarcasm by discussing various studies focusing on the terms. Next the first experiment is conducted comparing between various types of classification methods including some popular classifiers for text classification task. For the second experiment, different types of data preprocessing methods were compared and analyzed. Finally, the relationship between irony, sarcasm, and cyberbullying are discussed. The results are interesting as we observed high similarity between them.

This paper presents a novel method of analyzing morphosemantic patterns in language to the detect cyberbullying, or frequently appearing harmful messages and entries that aim to humiliate other users. The morphosemantic patterns represent a novel concept, with the assumption that analyzed elements can be perceived as a combination of morphological information, such as parts of speech, and semantic information, such as semantic roles, categories, etc. The patterns are further automatically extracted from the data containing harmful entries (cyberbullying) and non-harmful entries found on the informal websites of Japanese high schools. These website data were prepared and standardized by the Human Rights Center in Mie Prefecture, Japan. The patterns extracted in this way are further applied to a document classification task using the provided data in 10-fold cross-validation. The results indicate that morphosemantic sentence representation can be considered useful in the task of detecting the deceptive and provocative language used in cyberbullying.

BIM w planowaniu przestrzennym – omowienie mozliwości wykorzystania makiet BIM w procesie optymalizacji zarządzania przestrzenią w skali urbanistycznej

In this paper presents our research in automatic detection of emotionally loaded, or emotive sentences. We define the problem from a linguistic point of view assuming that emotive sentences stand out both lexically and grammatically. To verify this assumption we prepare a text classification experiment. In the experiment we apply language combinatorics approach to automatically extract emotive patterns from training sentences. The applied approach allows automatic extraction of not only widely used unigrams (tokens), or n-grams, but also more sophisticated patterns with disjointed elements. The results of experiments are explained with the use of means such as standard 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. The method reached results comparable to the state of the art, while the fact that it is fully automatic makes it more efficient and language independent.

This paper is an attempt at analyzing how much religious vocabulary (in this case Buddhist vocabulary taken from a large scale dictionary of Buddhist terms available online) is present in everyday Japanese social space (in this case in a repository of blog entries form the Ameba blog service) and thus in the consciousness of people. We also investigate and what associations (positive or negative) it generates, thus indicating the connotations associated with several Buddhist terms – whether expressions containing Buddhist vocabulary are considered proper or not from a moral point of view – as well as the emotional response of Internet users to Buddhist terminology.

We describe our attempt to apply a state-of-the-art sequential tagger – SVMTool – in the task of automatic part-of-speech annotation of the Ainu language, a critically endangered language isolate spoken by the native inhabitants of northern Japan. Our experiments indicated that it performs better than the custom system proposed in previous research (POST-AL), especially when applied to out-of-domain data. The biggest advantage of the model trained using SVMTool over the POST-AL tagger is its ability to guess part-of-speech tags for OoV words, with the accuracy of up to 63%.

PolEval is a SemEval-inspired evaluation campaign for natural language processing tools for Polish. Submitted tools compete againstone another within certain tasks selected by organizers, using available data and are evaluated according to pre-established procedures.It is organized since 2017 and each year the winning systems become the state-of-the-art in Polish language processing in the respectivetasks. In 2019 we have organized six different tasks, creating an even greater opportunity for NLP researchers to evaluate their systemsin an objective manner.

Curling is a winter sport often referred to as “chess on ice”. There are three factors influencing game performance in this game: physical factor, human factor, and strategic/tactical factor. The strategic/tactical factor is considered as the most important at the top level. In this paper, we report on new knowledge we obtained regarding the relationship between shot accuracy and difference in game score, and difference in correlation for each level in 378 games, covering around 60,000 shots as a research subject of Curling Informatics project.

We study the social problem of cyberbullying, defined as a new form of bullying that takes place in the Internet space. This paper proposes a method for automatic acquisition of seed words to improve performance of the original method for the cyberbullying detection by Nitta et al. [1]. We conduct an experiment exactly in the same settings to find out that the method based on a Web mining technique, lost over 30% points of its performance since being proposed in 2013. Thus, we hypothesize on the reasons for the decrease in the performance and propose a number of improvements, from which we experimentally choose the best one. Furthermore, we collect several seed word sets using different approaches, evaluate and their precision. We found out that the influential factor in extraction of harmful expressions is not the number of seed words, but the way the seed words were collected and filtered.

We developed a supporting solution for “cyberbullying” prevention based on recent discoveries in Artificial Intelligence and Natural Language Processing. Cyberbullying, defined as using the Internet to humiliate and slander other people has become a serious problem. In Japan members of the Parent–Teacher Association manually perform Web monitoring to stop cyberbullying activities. Unfortunately, reading through the whole Web manually is an impossible task. Although the complexity of cyberbullying makes it a problem unsolvable solely with the help of technology, we found that technology could make cyberbullying prevention more efficient. We developed a novel method of automatic detection of cyberbullying entries on the Internet. In the method we use seed words from three categories to calculate a semantic orientation score and then maximize the relevance of categories. The proposed method outperformed baseline settings in both laboratory and real world conditions. The developed system was deployed and tested in practice. After a year of testing we noticed a greater than 30 percent-point-drop in its performance. We hypothesize on the reasons for the drop. To regain the lost performance and retain it in the future we propose additional improvements including automatic acquisition and filtering of seed words. Experimentally selected optimal improvements regained much of the lost performance.

This paper presents game information analysis by utilizing a digital scorebook system, as the first tool for curling informatics, which supports coaches and players in realizing smart tactics and strategies in the sport of curling. Our research project, called “Curling Informatics,” aims to develop an environment to support curling strategies and tactics by realizing methods to record game information, perform analysis, and provide visualization and sharing of the information.We found a significant correlation between the differences in shot accuracies and scores from game information collected by our digital scorebook system for more than 200 games played by the Japanese national class. The results suggest that the difference in shot accuracies is related to the difference in game scores. This is valuable new knowledge to support strategic/tactical planning in curling games. However, the correlation for games involving world-class teams becomes weaker than for the Japanese national class because there is scarcely any difference in shot accuracies.

In this paper we introduce HEMOS (Humor-EMOji-Slang-based) system for fine-grained sentiment classification for the Chinese language using deep learning approach. We investigate the importance of recognizing the influence of humor, pictograms and slang on the task of affective processing of the social media. In the first step, we collected 576 frequent Internet slang expressions as a slang lexicon; then, we converted 109 Weibo emojis into textual features creating a Chinese emoji lexicon. In the next step, by performing two polarity annotations with new “optimistic humorous type” and “pessimistic humorous type” added to standard “positive” and “negative” sentiment categories, we applied both lexicons to attention-based bi-directional long short-term memory recurrent neural network (AttBiLSTM) and tested its performance on undersized labeled data. Our experimental results show that the proposed method can significantly improve the state-of-the-art methods in predicting sentiment polarity on Weibo, the largest Chinese social network.

Pictograms (emoticons/emojis) have been widely used in social media as a mean for graphical expression of emotions. People can express delicate nuances through textual information when supported with emoticons, and the effectiveness of computer-mediated communication (CMC) is also improved. Therefore it is important to fully understand the influence of emoticons on CMC. In this paper, we propose an emoticon polarity-aware recurrent neural network method for sentiment analysis of Weibo, a Chinese social media platform. In the first step, we analyzed the usage of 67 emoticons with racial expression used on Weibo. By performing a polarity annotation with a new “humorous type” added, we have confirmed that 23 emoticons can be considered more as humorous than positive or negative. On this basis, we applied the emoticons polarity in a Long Short-Term Memory recurrent neural network (LSTM) for sentiment analysis of undersized labelled data. Our experimental results show that the proposed method can significantly improve the precision for predicting sentiment polarity on Weibo.

The paper presents a method of optimizing Quantitative Learner’s Motivation Model with the use of genetic algorithm. It is focused on optimizing the formula for prediction of learning motivation by means of different weights for three values: interest, usefulness in the future and satisfaction. For the purpose of this optimization, we developed a C++ library that implements a genetic algorithm and an application in C# which uses that library with data acquired from questionnaires enquiring about those three elements. The results of the experiment showed improvement in the estimation of student’s learning motivation.

The problem of humiliating and slandering people through Internet, generally defined as cyberbullying (later: CB), has been recently noticed as a serious social problem disturbing mental health of Internet users. In Japan, to deal with the problem, members of Parent-Teacher Association (PTA) perform Internet Patrol – a voluntary work by reading through the whole Web contents to spot cyberbullying entries. To help PTA members we propose a novel method for automatic detection of malicious contents on the Internet. The method is based on a brute force search algorithm-inspired combinatorial approach to language modeling. The method automatically extracts sophisticated sentence patterns and uses them in classification. We tested the method on actual data containing cyberbullying provided by Human Rights Center. The results show our method outperformed previous methods. It is also more efficient as it requires minimal human effort.

In everyday life people use past events and their own knowledge to predict future events. In such everyday predictions people use widely available resources (newspapers, Internet). This study focused on sentences referring to the future, such as the one below, as one of such resource.

Experiments with language combinatorics in text classification: lessons learned and future implications

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.

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.

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. Index Terms—Intelligent systems, common sense, affect analysis, machine ethics

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.

In this paper, we present our progress so far in realization of project aimed to create a complex, modular humor-equipped conversational system. By complex, we mean that it should be able to: (1) detect users’ emotions, (2) detect users’ humorous behaviors and react to them properly, (3) generate humor according to users’ emotive states and (4) learn each user’s individual sense of humor. The research is conducted in Japanese. We chose puns as a relatively computable genre of humor. We describe a general outline of our system, as well as its four modules: humor detection module, emotion recognition module, response generator module and individualisation module. We present the algorithm of systems used in each module, along with some evaluation results.

The evaluation of subjective aspects of HCI, such as human-likeness, likeability or users' emotions towards computers is still quite a neglected issue, especially in the field of non-task oriented conversational systems (chatterbots). In this paper we try to bridge this gap by proposing a new methodology of evaluation. The methods presented were tested in our research on humor-equipped chatterbots. We describe them in details, discuss their drawbacks and usability. In one of the presented methods we used an emotiveness analysis system, which itself can be considered an AI tool, as it was used to detect users' emotions towards conversational systems, and to perform their automatic evaluation. We also propose some methods that we have not used yet, which, however, seem applicable in this field, such as brain scanning techniques. Finally, we give some ideas that should be addressed in the future.

Japan's domestic travel and tourism industry expenditure has been declining gradually since 1998 (from 33.5 in 1998 to 21.6 trillion JPY in 2016). Our research purpose is to construct a data analysis model to transform the collected data to a meaningful graphical format by using big data analytics techniques to discover anomalies and sustainable development possibilities for economy and tourism of Japan's rural areas, with a particular focus on the prefecture of Hokkaido, subprefecture of Okhotsk. To strengthen the reliability of this model we apply popular Monte Carlo simulation combined with Bayesian statistic and implement it on an Apache Spark platform to acquire results within the span of the study. Through this research, we focus on observing and analyzing interests, expectations and tendencies of Japanese people living in rural areas. From such collected information, we can obtain reasons for the decline of this sector’s impact on Japan’s economy. Measuring public awareness has become more efficient since the content generator role has been passed on to ordinary people. Therefore, the analysis of Big Data with the use of data science techniques has become important to comprehend human behavior from multiple points of view, including the scientific, economic, political, historical and sociological.

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 system's 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.

In this paper we present an innovative work on a multiagent joking conversational system. In our research so far we have shown that implementing humor into a chatterbot can visibly improve its performance. The results presented in this paper are the outcome of the next step of our work. They show that a multiagent system, combining a conversational agent, a pun generator and an emotiveness analysis engine, works reasonably well in interactions with users. In the setup used in this research, the emotiveness analysis agent analyses users' utterances and decides whether it is appropriate to tell a pun. Depending on the results of this analysis, the agent chooses either the pun generator, if the decision is that a joke should be told, or the non-humor-equipped agent when the decision is different. Two evaluation experiments were conducted: user (first person) focused and automatic (emotiveness-analysis-based). In both, we compared the performance of the multiagent joking system and a baseline (non-humorous) conversation agent. The results show that in both cases the humor-equipped engine was evaluated as better than the baseline agent. The results are discussed and some ideas for the future are given.

The topic of Human Computer Interaction (HCI) has been gathering more and more scientific attention of late. A very important, but often undervalued area in this field is human engagement. That is, a person's commitment to take part in and continue the interaction. In this paper we describe work on a humor-equipped casual conversational system (chatterbot) and investigate the effect of humor on a user's engagement in the conversation. A group of users was made to converse with two systems: one with and one without humor. The chat logs were then analyzed using an emotive analysis system to check user reactions and attitudes towards each system. Results were projected on Russell's two-dimensional emotiveness space to evaluate the positivity/negativity and activation/deactivation of these emotions. This analysis indicated emotions elicited by the humor-equipped system were more positively active and less negatively active than by the system without humor. The implications of results and relation between them and user engagement in the conversation are discussed. We also propose a distinction between positive and negative engagement.

We propose a method for affect analysis of textual input in Japanese supported with Web mining. The method is based on a pragmatic reasoning that emotional states of a speaker are conveyed by emotional expressions used in emotive utterances. It means that if an emotive expression is used in a sentence in a context described as emotive, the emotion conveyed in the text is revealed by the used emotive expression. The system ML-Ask (Emotive Elements / Expressions Analysis System) is constructed on the basis of this idea. An evaluation of the system is performed in which two evaluation methods are compared. To choose the most objective evaluation method we compare the most popular method in the field and a method proposed by us. The proposed evaluation method was shown to be more objective and revealed the strong and weak points of the system in detail. In the evaluation experiment ML-Ask reached human level in recognizing the general emotiveness of an utterance (0.83 balanced F-score) and 63% of human level in recognizing the specific types of emotions. We support the system with a Web mining technique to improve the performance of emotional state types extraction. In the Web mining technique emotive associations are extracted from the Web using co-occurrences of emotive expressions with morphemes of causality. The Web mining technique improved the performance of the emotional states types extraction to 85% of human performance.

In this research we focus on discriminating between emotive (emotionally loaded) and non-emotive sentences. We define the problem from a linguistic point of view assuming that emotive sentences stand out both lexically and grammatically. We verify this assumption experimentally by comparing two sets of such sentences in Japanese. The comparison is based on words, longer n-grams as well as more sophisticated patterns. In the classification weuse a novelunsupervised learning algorithm based on the idea of language combinatorics. The method reached results comparable to the state of the art, while the fact that it is fully automatic makes it more efficient and language independent.

This paper presents research in Contextual Affect Analysis (CAA) for the need of future application in intelligent agents, such as conversational agents or artificial tutors. The authors propose a new term, Computational Fronesis (CF), to embrace the tasks included in CAA applied to development of conversational agents such as artificial tutors. In tutor-student discourse it is crucial that the artificial tutor was able not only to detect user/student emotions, but also to verify toward whom they were directed and whether they were appropriate for the context of the conversation. Therefore, as the first task in CF the authors focus on verification of contextual appropriateness of emotions. They performed some of the first experiments in this task for the Japanese language and discuss future directions in development and implications of Computational Fronesis.

Emoticons are string of symbols representing body language in text-based communication. For a long time they have been considered as unnatural language entities. This chapter argues that, in over 40-year-long history of text-based communication, emoticons have gained a status of an indispensable means of support for text-based messages. This makes them fully a part of Natural Language Processing. The fact the emoticons have been considered as unnatural language expressions has two causes. Firstly, emoticons represent body language, which by definition is nonverbal. Secondly, there has been a lack of sufficient methods for the analysis of emoticons. Emoticons represent a multimodal (bimodal in particular) type of information. Although they are embedded in lexical form, they convey non-linguistic information. To prove this argument the authors propose that the analysis of emoticons was based on a theory designed for the analysis of body language. In particular, the authors apply the theory of kinesics to develop a state of the art system for extraction and analysis of kaomoji, Japanese emoticons. The system performance is verified in comparison with other emoticon analysis systems. Experiments showed that the presented approach provides nearly ideal results in different aspects of emoticon analysis, thus proving that emoticons possess features of multimodal expressions.