Asia-Pacific Conference on Conceptual Modelling, 2015
The spectacular evolution of sensor networks and the proliferation of location-sensing devices in... more The spectacular evolution of sensor networks and the proliferation of location-sensing devices in daily life activities are leading to an explosion of disparate spatio-temporal data. The collected data describes the movement of mobile objects used to construct what we call trajectory data. The diversity of these generated data has led to a variety of spatio-temporal models. In fact, the conceptual design can be achieved using either enhanced classical models such as spatio-temporal unied modeling language, spatio-temporal entity relationship, or ontological models such as web ontology language. Moreover, the diversity of conceptual formalisms highly increases the heterogeneity of sources as well as the diculty of interoperating between them. To reduce this complexity, we set up a high level formalism that covers the most important existing conceptual and ontological models. In fact, current abstract formalisms left out the representation of spatio-temporal properties. In this paper, we present a preliminary work that proposes an ontology-based pivot model for representing spatio-temporal sources.
The enormous evolution of positioning technologies and remote sensors is leading to big amounts o... more The enormous evolution of positioning technologies and remote sensors is leading to big amounts of disparate mobility data. Collected mobility data generates the need of modelling of such behaviour and the understanding of them which gave the rise of different models achieved either by classical conceptual modelling or by those based on ontology. Modelling and analysing trajectory data are still challenging because of the heterogeneity of trajectory data models and the complexity of establishing choices about domain’s consensual knowledge. To fulfil this objective, we propose a generic ontology that explains the semantics of these data and we define a trajectory data warehouse conceptual model based on the shared ontology in order to analyse trajectory data going from users’ short transactions to complex queries involving decision makers. The shared ontology that we propose is an OWL-DL formalism that covers common structures encountered in trajectories. We illustrate our work with a real case study.
Trajectory data warehouses were proposed, as an extension of traditional ones to take into accoun... more Trajectory data warehouses were proposed, as an extension of traditional ones to take into account mobility data provided by ubiquitous systems. As a new paradigm, it was adopted by users in various applications such as those related to marketing, agriculture, health care, etc. However the proposed conceptual models suffer from dispersed point of views that have to be unified in order to offer generic conceptual support for experts and clerical users. The goal of this paper is to propose a unified conceptual model able to unify different point of views through a generic description of fact and dimensions well adapted to new concepts imposed by the emergence of pervasive systems. Then, we project the proposed model on different use cases studied in the literature review.
Smart innovation, systems and technologies, May 28, 2017
Business Intelligence systems refer to technologies and tools responsible for collecting, storing... more Business Intelligence systems refer to technologies and tools responsible for collecting, storing and analyzing data to improve decision-making. In BI systems, users interact with data warehouse by formulating and launching sequences of queries aimed at exploring multidimensional data cubes. However, the volumes of data stored in a data warehouse can be very large and diversified. So, a big amount of irrelevant information returned as results to the user could make the data exploration process inefficient. That’s why, it’s necessary to help the user by guiding him in his exploration. In fact, query recommendation systems play a major role in reducing the effort of decision-makers to find the most interesting information. Several works dealing with query recommendation systems were presented in the last few years. This paper aims at providing a comprehensive review of literature on a query recommendation based on the exploration of data cubes. A benchmarking study of query recommendation methods is proposed. Several evaluation criteria are used to identify the existence of new investigations and future researches.
Concurrency and Computation: Practice and Experience, 2018
SummarySince the appearance of social networks, there was a historic increase of data. Unfortunat... more SummarySince the appearance of social networks, there was a historic increase of data. Unfortunately, terrorists are taking advantage of the easiness of accessing social networks and they have set up profiles to recruit, radicalize, and raise funds. Most of these profiles have pages that exist as well as new recruits to join the terrorist groups, see, and share information. Therefore, there is a potential need for detecting terrorist communities in social networks in order to search for key hints in posts that appear to promote the militants' cause. In order to remedy this problem, we first use a possibilistic‐clustering algorithm that allows more flexibility when assigning a social network profile to clusters (non‐terrorist, terrorist‐sympathizer, terrorist). Then, we introduce a new possibilistic flexible graph mining method to discover similar subgraphs by applying possibilistic similarity rather than using hard structural exact similarity. We experimentally show the efficien...
In recent years, text mining and sentiment analysis have received great attention due to the abun... more In recent years, text mining and sentiment analysis have received great attention due to the abundance of opinion data that exist in social networks such as Facebook, Twitter, etc. Sentiments are projected on these media using texts for expressing feelings such as friendship, social support, anger, happiness, etc. Existing sentiment analysis studies tend to identify user behaviors and state of minds but remain insufficient due to complexities in conveyed texts. In this research paper, we focus on the usage of text mining for sentiment classification. Illustration is performed on Tunisian users' statuses on "Facebook" posts during the "Arabic Spring" era. Our aim is to extract useful information, about users' sentiments and behaviors during this sensitive and significant period. For that purpose, we propose a method based on Support Vector Machine (SVM) and Naïve Bayes. We also construct a sentiment lexicon, based on the emoticons, interjections and acronyms', from extracted statuses updates. Moreover, we perform some comparative experiments between two machine learning algorithms SVM and Naïve Bayes through a training model for sentiment classification.
Advances in linguistics and communication studies, Jul 17, 2015
In this work, we focus on the application of text mining and sentiment analysis techniques for an... more In this work, we focus on the application of text mining and sentiment analysis techniques for analyzing Tunisian users' statuses updates on Facebook. We aim to extract useful information, about their sentiment and behavior, especially during the “Arabic spring” era. To achieve this task, we describe a method for sentiment analysis using Support Vector Machine and Naïve Bayes algorithms, and applying a combination of more than two features. The output of this work consists, on one hand, on the construction of a sentiment lexicon based on the Emoticons and Acronyms' lexicons that we developed based on the extracted statuses updates; and on the other hand, it consists on the realization of detailed comparative experiments between the above algorithms by creating a training model for sentiment classification.
Sentiment analysis is the field of study that analyzes people's opinions, sentiments, attitud... more Sentiment analysis is the field of study that analyzes people's opinions, sentiments, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, web mining, and text mining. In recent years, text mining and sentiment analysis are being in almost every business and social domain which study all human activities and key influencers of our behaviors. Even though there are, at present, several studies related to this theme, most of them focus mainly on English texts. The resources available for opinion mining in other languages, such as Arabic, are still limited. In this paper, we propose a new sentiment analysis system destined to classify users' opinions which is performed with a new corpus for Arabic language gathered from users' posts at the time of the Tunisian revolution. Furthermore, different experiments have been carried out on this corpus, using machine learning algorithms such as Support Vector Machines and Naïve Bayes.
A lot of research has been done on the problem of finding the k nearest neighbor to a query point... more A lot of research has been done on the problem of finding the k nearest neighbor to a query point. Existing studies are usually intended to work on static data. Even the minimal number of existing work done on dynamic objects has not solved the problems caused by their dynamic nature. The problem with KNN algorithms is how to keep the results fresh and avoid unnecessary computation cost each time the object changes position. This type of algorithm is in fact very used in many applications. In this document, a new challenge has been accepted to solve a complex problem. We propose a new approach to look for KNNs on continuously moving objects while guaranteeing a freshness of the results during a safety period during which the results of the query are always valid even if the object changes continuously its position. In order to take advantage of this type of algorithm in difficult situations such as the emergency decision-making process, we propose a new efficient algorithm to determine the K closest resources that are circulating in the same area of the query point. Our approach is progressive and relies on the Safe Region pruning method. As long as the object remains in its respective safe region, the new expensive computation is not necessary. The result of deep-seated experiments on our approach, validates its efficiency in terms of communication and calculation cost through a search restriction area method.
Asia-Pacific Conference on Conceptual Modelling, 2015
The spectacular evolution of sensor networks and the proliferation of location-sensing devices in... more The spectacular evolution of sensor networks and the proliferation of location-sensing devices in daily life activities are leading to an explosion of disparate spatio-temporal data. The collected data describes the movement of mobile objects used to construct what we call trajectory data. The diversity of these generated data has led to a variety of spatio-temporal models. In fact, the conceptual design can be achieved using either enhanced classical models such as spatio-temporal unied modeling language, spatio-temporal entity relationship, or ontological models such as web ontology language. Moreover, the diversity of conceptual formalisms highly increases the heterogeneity of sources as well as the diculty of interoperating between them. To reduce this complexity, we set up a high level formalism that covers the most important existing conceptual and ontological models. In fact, current abstract formalisms left out the representation of spatio-temporal properties. In this paper, we present a preliminary work that proposes an ontology-based pivot model for representing spatio-temporal sources.
The enormous evolution of positioning technologies and remote sensors is leading to big amounts o... more The enormous evolution of positioning technologies and remote sensors is leading to big amounts of disparate mobility data. Collected mobility data generates the need of modelling of such behaviour and the understanding of them which gave the rise of different models achieved either by classical conceptual modelling or by those based on ontology. Modelling and analysing trajectory data are still challenging because of the heterogeneity of trajectory data models and the complexity of establishing choices about domain’s consensual knowledge. To fulfil this objective, we propose a generic ontology that explains the semantics of these data and we define a trajectory data warehouse conceptual model based on the shared ontology in order to analyse trajectory data going from users’ short transactions to complex queries involving decision makers. The shared ontology that we propose is an OWL-DL formalism that covers common structures encountered in trajectories. We illustrate our work with a real case study.
Trajectory data warehouses were proposed, as an extension of traditional ones to take into accoun... more Trajectory data warehouses were proposed, as an extension of traditional ones to take into account mobility data provided by ubiquitous systems. As a new paradigm, it was adopted by users in various applications such as those related to marketing, agriculture, health care, etc. However the proposed conceptual models suffer from dispersed point of views that have to be unified in order to offer generic conceptual support for experts and clerical users. The goal of this paper is to propose a unified conceptual model able to unify different point of views through a generic description of fact and dimensions well adapted to new concepts imposed by the emergence of pervasive systems. Then, we project the proposed model on different use cases studied in the literature review.
Smart innovation, systems and technologies, May 28, 2017
Business Intelligence systems refer to technologies and tools responsible for collecting, storing... more Business Intelligence systems refer to technologies and tools responsible for collecting, storing and analyzing data to improve decision-making. In BI systems, users interact with data warehouse by formulating and launching sequences of queries aimed at exploring multidimensional data cubes. However, the volumes of data stored in a data warehouse can be very large and diversified. So, a big amount of irrelevant information returned as results to the user could make the data exploration process inefficient. That’s why, it’s necessary to help the user by guiding him in his exploration. In fact, query recommendation systems play a major role in reducing the effort of decision-makers to find the most interesting information. Several works dealing with query recommendation systems were presented in the last few years. This paper aims at providing a comprehensive review of literature on a query recommendation based on the exploration of data cubes. A benchmarking study of query recommendation methods is proposed. Several evaluation criteria are used to identify the existence of new investigations and future researches.
Concurrency and Computation: Practice and Experience, 2018
SummarySince the appearance of social networks, there was a historic increase of data. Unfortunat... more SummarySince the appearance of social networks, there was a historic increase of data. Unfortunately, terrorists are taking advantage of the easiness of accessing social networks and they have set up profiles to recruit, radicalize, and raise funds. Most of these profiles have pages that exist as well as new recruits to join the terrorist groups, see, and share information. Therefore, there is a potential need for detecting terrorist communities in social networks in order to search for key hints in posts that appear to promote the militants' cause. In order to remedy this problem, we first use a possibilistic‐clustering algorithm that allows more flexibility when assigning a social network profile to clusters (non‐terrorist, terrorist‐sympathizer, terrorist). Then, we introduce a new possibilistic flexible graph mining method to discover similar subgraphs by applying possibilistic similarity rather than using hard structural exact similarity. We experimentally show the efficien...
In recent years, text mining and sentiment analysis have received great attention due to the abun... more In recent years, text mining and sentiment analysis have received great attention due to the abundance of opinion data that exist in social networks such as Facebook, Twitter, etc. Sentiments are projected on these media using texts for expressing feelings such as friendship, social support, anger, happiness, etc. Existing sentiment analysis studies tend to identify user behaviors and state of minds but remain insufficient due to complexities in conveyed texts. In this research paper, we focus on the usage of text mining for sentiment classification. Illustration is performed on Tunisian users' statuses on "Facebook" posts during the "Arabic Spring" era. Our aim is to extract useful information, about users' sentiments and behaviors during this sensitive and significant period. For that purpose, we propose a method based on Support Vector Machine (SVM) and Naïve Bayes. We also construct a sentiment lexicon, based on the emoticons, interjections and acronyms', from extracted statuses updates. Moreover, we perform some comparative experiments between two machine learning algorithms SVM and Naïve Bayes through a training model for sentiment classification.
Advances in linguistics and communication studies, Jul 17, 2015
In this work, we focus on the application of text mining and sentiment analysis techniques for an... more In this work, we focus on the application of text mining and sentiment analysis techniques for analyzing Tunisian users' statuses updates on Facebook. We aim to extract useful information, about their sentiment and behavior, especially during the “Arabic spring” era. To achieve this task, we describe a method for sentiment analysis using Support Vector Machine and Naïve Bayes algorithms, and applying a combination of more than two features. The output of this work consists, on one hand, on the construction of a sentiment lexicon based on the Emoticons and Acronyms' lexicons that we developed based on the extracted statuses updates; and on the other hand, it consists on the realization of detailed comparative experiments between the above algorithms by creating a training model for sentiment classification.
Sentiment analysis is the field of study that analyzes people's opinions, sentiments, attitud... more Sentiment analysis is the field of study that analyzes people's opinions, sentiments, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, web mining, and text mining. In recent years, text mining and sentiment analysis are being in almost every business and social domain which study all human activities and key influencers of our behaviors. Even though there are, at present, several studies related to this theme, most of them focus mainly on English texts. The resources available for opinion mining in other languages, such as Arabic, are still limited. In this paper, we propose a new sentiment analysis system destined to classify users' opinions which is performed with a new corpus for Arabic language gathered from users' posts at the time of the Tunisian revolution. Furthermore, different experiments have been carried out on this corpus, using machine learning algorithms such as Support Vector Machines and Naïve Bayes.
A lot of research has been done on the problem of finding the k nearest neighbor to a query point... more A lot of research has been done on the problem of finding the k nearest neighbor to a query point. Existing studies are usually intended to work on static data. Even the minimal number of existing work done on dynamic objects has not solved the problems caused by their dynamic nature. The problem with KNN algorithms is how to keep the results fresh and avoid unnecessary computation cost each time the object changes position. This type of algorithm is in fact very used in many applications. In this document, a new challenge has been accepted to solve a complex problem. We propose a new approach to look for KNNs on continuously moving objects while guaranteeing a freshness of the results during a safety period during which the results of the query are always valid even if the object changes continuously its position. In order to take advantage of this type of algorithm in difficult situations such as the emergency decision-making process, we propose a new efficient algorithm to determine the K closest resources that are circulating in the same area of the query point. Our approach is progressive and relies on the Safe Region pruning method. As long as the object remains in its respective safe region, the new expensive computation is not necessary. The result of deep-seated experiments on our approach, validates its efficiency in terms of communication and calculation cost through a search restriction area method.
Uploads
Papers by Jalel Akaichi