International Journal on Artificial Intelligence Tools

Characterizing users and tracking their activities in online classified ads is a topic of great importance. However, some of the underlying problems associated with modeling users and detecting their behavioral changes have not been well-studied.

In this paper, we develop a probabilistic framework for characterizing users and quantifying some of the spatial and temporal variations in their posts. Our work on characterizing users study the problem in the context of detecting if a user belongs to a class, based on the ads the user has posted. Our approach is based on user profiling, where given statistics on user posts, the affinity of a user to a class is estimated. We show how profiles can be constructed with and without training data and report the effectiveness of our approaches in detecting two user classes business and non-business.

Our work on quantifying changes due to spatial and temporal variations is based on a probabilistic model of user behavior and a generative model that can predict ad posts from each location. We evaluate these models on a relatively large set of users and ads, and report our results on two classes of users monitored over a period of almost a year.

Semantic Web knowledge bases, in particular large cross-domain data, are often noisy, incorrect, and incomplete with respect to type information. This incompleteness can be reduced, as previous work shows, with automatic type prediction methods. Most knowledge bases contain an ontology defining a type hierarchy, and, in general, entities are allowed to have multiple types (classes of an instance assigned with the rdf:type relation). In this paper, we exploit these characteristics and formulate the type prediction problem as hierarchical multi classification, where the labels are types. We evaluate different sets of features, including entity embeddings, which can be extracted from the knowledge graph exclusively. We propose SLCN, a modification of the local classifier per node approach, which performs feature selection, instance sampling, and class balancing for each local classifier with the objective of improving scalability. Furthermore, we explore different variants of creating features for the classifier, including both graph and latent features. We compare the performance of our proposed method with the state-of-the-art type prediction approach and popular hierarchical multilabel classifiers, and report on experiments with large-scale cross-domain RDF datasets.

Access to information has been made easier in different domains that range from multimedia content, books, music, news, etc. To deal with the huge amount of alternatives, recommendation systems have been often used as a solution to filter the options and provide suggestions of items that might be of interest to an user. The news domain introduces additional challenges due not only to the large amount of new items produced daily but also due to their ephemeral timelife.

In this paper, a news recommendation system which combines content-based and georeferenced techniques in a mobility scenario, is proposed. Taking into account the volatility of the information, short-term and long-term user profiles are considered and implicitly built. Besides tracking users’ clicks, the system infers different levels of interest an article has by tracking and weighting each action in the system and in social networks. Impact of the different fields that make up a news is also taken into account by following the inverted pyramid model that assumes different levels of importance to each paragraph of the article. The solution was tested with a population of volunteers and results indicate that the quality of the recommendation approach is acknowledged by the users.

Although a Finite State Machine (FSM) is easy to implement the behaviors of None-Player Characters (NPC) in computer games, it is difficult to maintain and control the behaviors with increasing the number of states. Alternatively, Behavior Tree (BT), which is a tree of hierarchical nodes to control the ow of decision making, is widely used in computer games to address the scalability issues. This paper reviews the structure and semantics of BTs in computer games. Different techniques to automatically learn and build BTs as well as strengths and weaknesses of these techniques are discussed. This paper provides a taxonomy of BT features and shows to what extent these features are taken into account in computer games. Finally, the paper shows how BTs are used in practice in the gaming industry.

Natural Language Understanding (NLU) is an old and really challenging field with a variety of research work published on it. In this paper we present a formal language methodology based on a state machine for efficiently representing natural language events/actions and their associations in well-written documents. The methodology consists of the following steps. We firstly apply Anaphora Resolution (AR) to the pre-processing natural language text. Then we extract the kernel(s) of each sentence. These kernels are formally represented using a formal language, (Glossa) to map the language expressions (kernels) into Stochastic Petri Nets (SPN) graphs. Finally we apply a set of rules to combine the SPN graphs in order to achieve the associations of actions/events in time. Special emphasis of this paper is the mapping of kernels of NL sentences into SPN graphs. Note that this work does not cover all the aspects of the NLU. Examples of SPN graphs of different NL texts, produced by our proposed methodology are given.

The most important characteristic of semi-supervised learning methods is the combination of available unlabeled data along with an enough smaller set of labeled examples, so as to increase the learning accuracy compared with the default procedure of supervised methods, which on the other hand use only the labeled data during the training phase. In this work, we have implemented a hybrid Self-trained system that combines a Support Vector Machine, a Decision Tree, a Lazy Learner and a Bayesian algorithm using a Stacking variant methodology. We performed an in depth comparison with other well-known Semi-Supervised classification methods on standard benchmark datasets and we finally reached to the point that the presented technique had better accuracy in most cases.

Dung’s argumentation frameworks are adopted in a variety of applications, from argument-mining, to intelligence analysis and legal reasoning. Despite this broad spectrum of already existing applications, the mostly adopted solver—in virtue of its simplicity—is far from being comparable to the current state-of-the-art solvers. On the other hand, most of the current state-of-the-art solvers are far too complicated to be deployed in real-world settings. In this paper we provide and extensive description of jArgSemSAT, a Java re-implementation of ArgSemSAT. ArgSemSAT represents the best single solver for argumentation semantics with the highest level of computational complexity. We show that jArgSemSAT can be easily integrated in existing argumentation systems (1) as an off-the-shelf, standalone, library; (2) as a Tweety compatible library; and (3) as a fast and robust web service freely available on the Web. Our large experimental analysis shows that despite being written in Java, jArgSemSAT would have scored in most of the cases among the three bests solvers for the two semantics with highest computational complexity “Stable and Preferred” in the last competition on computational models of argumentation.

A spatial co-location pattern is a group of spatial objects whose instances are frequently located in the same region. The spatial co-location pattern mining problem has been investigated extensively in the past due to its broad range of applications. In this paper we study this problem for fuzzy objects. Fuzzy objects play an important role in many areas, such as the geographical information system and the biomedical image database. In this paper, we propose two new kinds of co-location pattern mining for fuzzy objects, single co-location pattern mining (SCP) and range co-location pattern mining (RCP), to mining co-location patterns at a membership threshold or within a membership range. For efficient SCP mining, we optimize the basic mining algorithm to accelerate the co-location pattern generation. To improve the performance of RCP mining, effective pruning strategies are developed to significantly reduce the search space. The efficiency of our proposed algorithms as well as the optimization techniques are verified with an extensive set of experiments.

Vehicle routing is a class of combinatorial optimization problems arising in the industry of transportation and logistics. The goal of these problems is to compute an optimal route plan for a set of vehicles for serving transport requests of customers. There are many variants of the vehicle routing problems: routing for delivering goods, routing for demand responsive transport (taxi, school bus, …). Each problem might have different constraints, objectives. In this paper, we introduce a Constraint-Based Local Search (CBLS) framework for general offline and online vehicle routing problems. We extend existing neighborhood structures in the literature by proposing new neighborhoods to facilitate the resolution of different class of vehicle routing problems in a unified platform. A novel feature of the framework is the available APIs for online vehicle routing problems where requests arrive online during the execution of the computed route plan. Experimental results on three vehicle routing problems (the min-max capacitated vehicle routing problem, the multi-vehicle covering tour problem, and the online people-andparcel share-a-ride taxis problem) show the modelling flexibility, genericity, extensibility and efficiency of the proposed framework.

Aiming to an automatic sound recognizer for radio broadcasting events, a methodology of clustering the audio feature space using the discrimination ability of the audio descriptors as a criterion, is investigated in this work. From a given and close set of audio events, commonly found in broadcast news transmissions, a large set of audio descriptors is extracted and their data-driven ranking of relevance is clustered, providing a more robust feature selection. The clusters of the feature space are feeding machine learning algorithms implemented as classification models during the experimental evaluation. This methodology showed that support vector machines provide significantly good results, considering the achieved accuracy due to their ability of coping well in high dimensionality experimental conditions.