Fazel Keshtkar

Using sentiment orientation features for mood classification in blogs

In this paper we explore the task of mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard machine learning approach. We also show that using sentiment orientation features improves the performance of classification. We used the Livejournal blog corpus as a dataset to train and evaluate our method.

Segmentation of Dental Radiographs Using a Swarm Intelligence Approach

One of the most complex tasks in digital image processing is image segmentation. This paper proposes a novel image segmentation algorithm that uses a biologically inspired technique based on swarm intelligence and a cellular automata model. The proposed swarm intelligence-based algorithm operates on the image pixel data and a region/neighborhood map to form a context in which they can merge. The swarm intelligent algorithm also tries to find similar pixels using a sensor function, which is then utilized by swarm agents to determine the next appreciate pixel in the region/segment area. In addition, the paper introduces a cellular automata-based dynamic flow algorithm to guide swarm agents to choose the best possible advancing direction to avoid traffic jam and inconsistency. The suggested image segmentation strategy is tested on a set of dental radiographs

A hierarchical approach to mood classification in blogs

In this article, we explore the task of mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard machine learning approach. We also show that using sentiment orientation features improves the performance of classification. We used the Livejournal blog corpus as a data set to train and evaluate our method. We present extensive error analysis and discuss the difficulty of the task.

Context-Based Speech Act Classification in Intelligent Tutoring Systems

In intelligent tutoring systems with natural language dialogue, speech act classification, the task of detecting learners’ intentions, informs the system’s response mechanism. In this paper, we propose supervised machine learning models for speech act classification in the context of an online collaborative learning game environment. We explore the role of context (i.e. speech acts of previous utterances) for speech act classification. We compare speech act classification models trained and tested with contextual and non-contextual features (contents of the current utterance). The accuracy of the proposed models is high. A surprising finding is the modest role of context in automatically predicting the speech acts.

A BOOTSTRAPPING METHOD FOR EXTRACTING PARAPHRASES OF EMOTION EXPRESSIONS FROM TEXTS

Because paraphrasing is one of the crucial tasks in natural language understanding and generation, this paper introduces a novel technique to extract paraphrases for emotion terms, from nonparallel corpora. We present a bootstrapping technique for identifying paraphrases, starting with a small number of seeds. WordNet Affect emotion words are used as seeds. The bootstrapping approach learns extraction patterns for six classes of emotions. We use annotated blogs and other data sets as texts from which to extract paraphrases, based on the highest scoring extraction patterns. The results include lexical and morphosyntactic paraphrases, that we evaluate with human judges.

Knowledge-based image segmentation using swarm intelligence techniques

Intelligent techniques such as swarm intelligence techniques rarely have been used for image segmentation or boundary detection. The limited increasing number of agents in the environment and how to find efficiently the right threshold in an image, develop a flexible design, and fully autonomous system that supports different platforms makes the task challenging. Considering challenges this paper presents a swarm-based intelligent technique for image segmentation that is based on a fully agent-based model system, called swarm intelligence-based image segmentation (SIBIS). SIBIS adopts a cellular automata technique where the swarm of agents navigate through the image and operate on their pixels and local regions. Three features such as swarm intelligence, agent-based modelling and cellular automata are integrated to make SIBIS efficient. SIBIS system can find the image segmentation threshold automatically without changing the background or the texture of the image.

Using Data Mining Techniques to Detect the Personality of Players in an Educational Game

One of the goals of Educational Data Mining is to develop the methods for student modeling based on educational data, such as; chat conversation, class discussion, etc. On the other hand, individual behavior and personality play a major role in Intelligent Tutoring Systems (ITS) and Educational Data Mining (EDM). Thus, to develop a user adaptable system, the student’s behaviors that occurring during interaction has huge impact EDM and ITS. In this chapter, we introduce a novel data mining techniques and natural language processing approaches for automated detection student’s personality and behaviors in an educational game (Land Science) where students act as interns in an urban planning firm and discuss in groups their ideas. In order to apply this framework, input excerpts must be classified into one of six possible personality classes. We applied this personality classification method using machine learning algorithms, such as: Naive Bayes, Support Vector Machine (SVM) and Decision Tree.

A pattern-based model for generating text to express emotion

In this paper we introduce a novel pattern-based model for generating emotion sentences. Our model starts with initial patterns, then constructs extended patterns. From the extended patterns, we chose good patterns that are suitable for generating emotion sentences. We also introduce a sentence planning module, which provides rules and constraints for our model. We present some examples and results for our model. We show that the model can generate various types of emotion sentences, either from semantic representation of input, or by choosing the pattern and the desired emotion class.

Novice-Friendly Natural Language Generation Template Authoring Environment

Natural Language Generation (NLG) systems can make data accessible in an easily digestible textual form; but using such systems requires sophisticated linguistic and sometimes even programming knowledge. We have designed and implemented an environment for creating and modifying NLG templates that requires no programming knowledge, and can operate with a minimum of linguistic knowledge. It allows specifying templates with any number of variables and dependencies between them. It internally uses SimpleNLG to provide the linguistic background knowledge. We test the performance of our system in the context of an interactive simulation game.

Visual Development Process for Automatic Generation of Digital Games Narrative Content

Users of Natural Language Generation systems are required to have sophisticated linguistic and sometimes even programming knowledge, which has hindered the adoption of this technology by individuals outside the computational linguistics research community. We have designed and implemented a visual environment for creating and modifying NLG templates which requires no programming ability and minimum linguistic knowledge. It allows specifying templates with any number of variables and dependencies between them. Internally, it uses SimpleNLG to provide the linguistic background knowledge. We tested the performance of our system in the context of an interactive simulation game. We describe the templates used for testing and show examples of sentences that our system generates from these templates.