The area of argumentation theory is an increasingly important area of artificial intelligence and mechanisms that are able to automatically detect the argument structure provide a novel area of research. This paper considers the use of kernel methods for argumentation detection and classification. It shows that a classification accuracy of 65%, can be attained using Natural Language Processing based kernel approaches, which do not require any heuristic choice of features.

In NL2OCL project, we aim to translate English specification of constraints to formal constraints such as OCL (Object Constraint Language). In English to OCL translation, our contribution is a semantic analyzer that uses the output of the Stanford parser for shallow and deep semantic parsing. Our analysis of the output of shallow semantic parsing showed that semantic roles were mis-identified for a few English constraints due to semantic ambiguity. Similarly, in deep semantic parsing, it is difficult to resolve scope of quantifier operators due to scope ambiguity that is another sub-type of semantic ambiguity. In this paper, we highlight the identified cases of semantic ambiguities in English constraints. We also present a novel approach to automatically resolve the identified cases of the semantic ambiguities. The presented approach is also evaluated to show that by addressing the identified cases of semantic ambiguities, we can generate more accurate and complete formal (OCL) specifications.

Recently cross-document integration and reconciliation of extracted information became of interest to researchers in Arabic natural language processing. Given a set of documents $A$, we use Arabic morphological analysis, finite state machines, and graph transformations to extract named entities N a and relations R a expressed as edges in a graph G = ( N a, R a ). We use the same techniques to extract entities N b and relations R b from a separate set of documents B. We use G to disambiguate N b and R and we integrate the resulting entities back into G by annotating the nodes and edges in G with elements from N b . We apply our approach in an iterative manner. Our results show a significant increase in accuracy from 41% to 93% after applying this cross-document NLP methodology to hadith and biography documents.

This paper compared the linguistic and psychological word uses in English and Chinese languages with LIWC (Linguistic Inquiry and Word Count) programs. A Principal Component Analysis uncovered six linguistic and psychological components, among which five components were significantly correlated. The correlated components were ranked as Negative Valence (r=.92), Embodiment (r=.88), Narrative (r=.68), Achievement (r=.65), and Social Relation (r=.64). However, the results showed the order of the representative features differs in two languages and certain word categories co-occurred with different components in English and Chinese. The differences were interpreted from the perspective of distinctive eastern and western cultures.

Are the words that people use indicative of their personality type preferences? In this paper, it is hypothesized that word-usage is not independent of personality type, as measured by the Myers-Briggs Type Indicator (MBTI) personality assessment tool. In-class writing samples were taken from 40 graduate students along with the MBTI. The experiment utilizes naïve Bayes classifiers and Support Vector Machines (SVMs) in an attempt to guess an individual’s personality type based on their word-choice. Classification is also attempted using emotional, social, cognitive, and psychological dimensions elicited by the analysis software, Linguistic Inquiry and Word Count (LIWC). The classifiers are evaluated with 40 distinct trials (leave-one-out cross validation), and parameters are chosen using leave-one-out cross validation of each trial’s training set. The experiment showed that the naïve Bayes classifiers (word-based and LIWC-based) outperformed the SVMs when guessing Sensing-Intuition (S-N) and Thinking-Feeling (T-F).

Web 2.0 has changed the ways people communicate, collaborate, and express their opinions and sentiments. But despite social data on the Web being perfectly suitable for human consumption, they remain hardly accessible to machines. To bridge the cognitive and affective gap between word-level natural language data and the concept-level sentiments conveyed by them, we developed SenticNet 2, a publicly available semantic and affective resource for opinion mining and sentiment analysis. SenticNet 2 is built by means of sentic computing, a new paradigm that exploits both AI and Semantic Web techniques to better recognize, interpret, and process natural language opinions. By providing the semantics and sentics (that is, the cognitive and affective information) associated with over 14,000 concepts, SenticNet 2 represents one of the most comprehensive semantic resources for the development of affect-sensitive applications in fields such as social data mining, multimodal affective HCI, and social media marketing.

This project focuses on artificial social interactions where things get nasty and mean. The purpose is training in social 'facework' -- managing the situation so that participants maintain their social dignity or 'face'. This can be especially delicate in cross-cultural contexts, where assumptions about social protocols and the emotional associations of utterances and gestures may differ. The purpose of this project is two-fold. First, it is intended as a training system, so that users might learn the do's and don'ts of social interactions in different cultures and different situations. The knowledge base draws from existing theories of diplomacy, facework, and (im)politeness theory. The other goal is to provide a platform for observation and experimentation of social interaction in an artificial, virtual setting in order to improve these theories.

Researchers have recognized the importance of classifying personality through discourse for many years. However, this line of research tends to focus almost exclusively on the personality categories known as the Big Five factors. Though this information is certainly valuable, it may also be useful to categorize personality based on the Leary’s Interpersonal Circumplex model which emphasizes a predictive function. In this paper we construct the data set for personality annotation among six dimensions (based on a coding scheme developed from Leary’s Interpersonal Circumplex) for players using a chat interaction in an epistemic game, Land Science. Our results indicate that overall personality annotation is reliable (Average Kappa = 0.65) with the highest reliability for the competitive dimension and the lowest reliability for the leading dimension.

Depression and other mood disorders are common and disabling disorders. We present work towards an objective diagnostic aid supporting clinicians using affective sensing technology with a focus on acoustic and statistical features from spontaneous speech. This work investigates differences in expressing positive and negative emotions in depressed and healthy control subjects as well as whether initial gender classification increases the recognition rate. To this end, spontaneous speech from interviews of 30 subjects of each depressed and controls was analysed, with a focus on questions eliciting positive and negative emotions. Using HMMs with GMMs for classification with 30-fold cross-validation, we found that MFCC, energy and intensity features gave highest recognition rates when female and male subjects were analysed together. When the dataset was first split by gender, log energy and shimmer features, respectively, were found to give the highest recognition rates in females, while it was loudness for males. Overall, correct recognition rates from acoustic features for depressed female subjects were higher than for male subjects. Using statistical features, we found that the response time and average syllable duration were longer in depressed subjects, while the interaction involvement and articulation rate were higher in control subjects.

In this paper we present a new method for ontology selection in a reuse context. The novel feature of this method is the iterative selection of the reused ontologies. Ontology selection is guided by the user according to his requirements and his perception to the target domain. Starting from a first selected ontology, the concepts with the weakest density are identified then the ontology developer is enabled to choose among them the ones to be refined in order to cover a specific scope of the domain.