|
| Titre : |
Useful event detection on online social medias |
| Type de document : |
document électronique |
| Auteurs : |
Malika Noui, Auteur ; Abdelaziz Lakhfif, Directeur de thèse |
| Editeur : |
Sétif:UFA1 |
| Année de publication : |
2025 |
| Importance : |
1 vol (109 f.) |
| Format : |
29 cm |
| Langues : |
Anglais (eng) |
| Catégories : |
Thèses & Mémoires:Informatique
|
| Mots-clés : |
Social media
NLP
Useful event detection
Transformers based models
BERT. |
| Index. décimale : |
004 - Informatique |
| Résumé : |
Social media has transformed the Internet into a dynamic platform, enabling users to
create, share, and comment on textual content related to various categories of events.
However, processing data derived from social media presents a significant challenges for
event detection and classification due to the massive volume of information and the often
informal structure of texts. To address this issue, research has highlighted the importance
of corpus and datasets, which are indispensable for analyzing and processing textual content
from social media, particularly for event detection(ED) and classification. In this
thesis, we propose solutions for event detection and classification, with a specific focus on
tweets published on the social media platform Twitter. Event detection and classification
are especially crucial in numerous fields, such as politics, healthcare, disaster management,
science, sports, economics and others. Our contributions include the construction
of datasets and the development of advanced models for detection and classification,
leveraging recent advancements in deep learning, notably transformer architectures such
as BERT model. Specifically, a variety of model variants have been experimented to
address different contexts and requirements, these include BERT Base, BERT Large,
DistilBERT, CAMeLBERT, ARAELECTRA, among others. Our experiments with these
models have shown promising results compared to the state of the art, achieving impressive
accuracy rates that have reached more than 94% in some cases. These out comes
underscore the relevance of our approaches and their potential applications across various
domains, specifically in event detection and classification of text in OSM. |
| Note de contenu : |
Sommaire
Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Dedications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
List of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
1 Introduction vi
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Research Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.3 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.4 Publications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.5 Thesis Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Background 6
2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Defining an event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.1 What is an event? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.2 Types of events . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.2.3 Useful event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.3.1 Useful event in Politics . . . . . . . . . . . . . . . . . . . . 9
2.2.3.2 Useful event in Health . . . . . . . . . . . . . . . . . . . . 9
2.2.3.3 Useful event in Disaster . . . . . . . . . . . . . . . . . . . 9
2.2.3.4 Useful event in Social sciences . . . . . . . . . . . . . . . . 10
2.2.3.5 Useful event in Sport . . . . . . . . . . . . . . . . . . . . . 10
2.2.4 Definition of Event detection . . . . . . . . . . . . . . . . . . . . . . 10
2.2.5 Event detection methods . . . . . . . . . . . . . . . . . . . . . . . 11
2.3 Event Detection on OSM . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.1 Definition of social media . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.2 Social media data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4 Event Detection on Twitter . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4.1 Presentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4.2 Functionalities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.4.3 Twitter usage statistics . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.4.4 Challenges in using Twitter as a source of information . . . . . . . . 14
2.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3 Techniques and Methods 16
3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2 Similarities based methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.1 Texts similarities . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.2 Measures of Similarity . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.1 Cosine Similarity . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.2 Jaccard Coefficient . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.3 Dice Coefficient . . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.4 Overlap Coefficient . . . . . . . . . . . . . . . . . . . . . . 20
3.2.2.5 Euclidean distance(L2) . . . . . . . . . . . . . . . . . . . . 20
3.2.2.6 Manhattan distance(L1) . . . . . . . . . . . . . . . . . . . 20
3.3 Machine Learning based methods . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.1 Supervised learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.1.1 Neural Networks (ANN) . . . . . . . . . . . . . . . . . . . 21
3.3.1.2 Recurrent Neural Network (RNN) . . . . . . . . . . . . . . 22
3.3.2 Unsupervised learning . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.2.1 K-means . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.2.2 Agglomerative clustering . . . . . . . . . . . . . . . . . . . 23
3.3.2.3 K-Medoids . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.4 Deep Learning-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.4.1 Long short-term memory (LSTM) . . . . . . . . . . . . . . . . . . . 24
3.4.2 Gated Recurrent Neural Network(GRU) . . . . . . . . . . . . . . . 25
3.5 Word embedding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
3.6 Transformers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
3.6.1 Transformer model . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.6.2 Pretrained Models: BERT . . . . . . . . . . . . . . . . . . . . . . . 28
3.7 Functions of Activation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
3.7.1 The function of Linear Activation . . . . . . . . . . . . . . . . . . . 29
3.7.2 Non-Linear Function of Activation . . . . . . . . . . . . . . . . . . 30
3.7.2.1 Sigmoid Function . . . . . . . . . . . . . . . . . . . . . . 30
3.7.2.2 Tanh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
3.7.2.3 Sigmoid and Tanh comparison . . . . . . . . . . . . . . . . 32
3.7.2.4 ReLU (Rectified Linear Unit) Function . . . . . . . . . . . 32
3.7.2.5 Exponential Linear Units(ELU) . . . . . . . . . . . . . . . 33
3.7.2.6 Softmax Function . . . . . . . . . . . . . . . . . . . . . . . 34
3.7.2.7 SoftPlus Function . . . . . . . . . . . . . . . . . . . . . . 34
3.8 Evaluation metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.8.1 Confusion Matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.8.2 Measuring Performance . . . . . . . . . . . . . . . . . . . . . . . . . 36
3.9 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
4 Literature Review 41
4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2 Event Detection Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1 Datasets from Twitter . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1.1 Event collections . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1.2 EveTAR collections . . . . . . . . . . . . . . . . . . . . . . 42
4.2.2 Datasets from the general domain . . . . . . . . . . . . . . . . . . . 43
4.3 Event Detection techniques . . . . . . . . . . . . . . . . . . . . . . . . . . 43
4.3.1 Specified Event Detection(SED) . . . . . . . . . . . . . . . . . . . . 43
4.3.2 Unspecified Event Detection(UED) . . . . . . . . . . . . . . . . . . 43
4.4 Approaches for event detection . . . . . . . . . . . . . . . . . . . . . . . . 44
4.5 Different techniques and methods proposed for event detection and classification
on OSM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
4.6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
5 Frameworks and Experimentations 54
5.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
5.2 Building a Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
5.2.1 Collecting Tweets for the Dataset . . . . . . . . . . . . . . . . . . . 55
5.2.2 Adapting Datasets for Event Detection and Classification . . . . . . 57
5.2.3 Dataset Statistics . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
5.3 AI-based Models for Event Detection and Classification . . . . . . . . . . . 59
5.3.1 Supervised Learning Based Models . . . . . . . . . . . . . . . . . . 59
5.3.1.1 BERT+LSTM model for events classification . . . . . . . 60
5.3.1.2 LSTM based model for Multi-classifaction . . . . . . . . . 68
5.3.1.3 Hybrid Similarity and BERT-Based Models for Event Detection
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83
5.3.2 Unsupervised based Models . . . . . . . . . . . . . . . . . . . . . . 92
5.3.2.1 Clustering and labeling Algorithm for English Dataset . . 94
5.3.2.2 Clustering and labeling Algorithm for Arabic Dataset . . . 95
5.3.2.3 Experiments and evaluations . . . . . . . . . . . . . . . . 96
5.3.2.4 Clustering algorithms for English tweets . . . . . . . . . . 96
5.3.2.5 Clustering performance of DistilBERT and TF-IDF . . . . 100
5.3.2.6 Clustering algorithms for Arabic tweets . . . . . . . . . . 100
5.3.2.7 Analysis result According to the Number of Clusters . . . 103
5.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 106
6 Conclusions and Future Works 107
6.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107
6.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109
|
| Côte titre : |
DI/0088 |
Useful event detection on online social medias [document électronique] / Malika Noui, Auteur ; Abdelaziz Lakhfif, Directeur de thèse . - [S.l.] : Sétif:UFA1, 2025 . - 1 vol (109 f.) ; 29 cm. Langues : Anglais ( eng)
| Catégories : |
Thèses & Mémoires:Informatique
|
| Mots-clés : |
Social media
NLP
Useful event detection
Transformers based models
BERT. |
| Index. décimale : |
004 - Informatique |
| Résumé : |
Social media has transformed the Internet into a dynamic platform, enabling users to
create, share, and comment on textual content related to various categories of events.
However, processing data derived from social media presents a significant challenges for
event detection and classification due to the massive volume of information and the often
informal structure of texts. To address this issue, research has highlighted the importance
of corpus and datasets, which are indispensable for analyzing and processing textual content
from social media, particularly for event detection(ED) and classification. In this
thesis, we propose solutions for event detection and classification, with a specific focus on
tweets published on the social media platform Twitter. Event detection and classification
are especially crucial in numerous fields, such as politics, healthcare, disaster management,
science, sports, economics and others. Our contributions include the construction
of datasets and the development of advanced models for detection and classification,
leveraging recent advancements in deep learning, notably transformer architectures such
as BERT model. Specifically, a variety of model variants have been experimented to
address different contexts and requirements, these include BERT Base, BERT Large,
DistilBERT, CAMeLBERT, ARAELECTRA, among others. Our experiments with these
models have shown promising results compared to the state of the art, achieving impressive
accuracy rates that have reached more than 94% in some cases. These out comes
underscore the relevance of our approaches and their potential applications across various
domains, specifically in event detection and classification of text in OSM. |
| Note de contenu : |
Sommaire
Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Dedications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
List of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
1 Introduction vi
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Research Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.3 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.4 Publications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.5 Thesis Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Background 6
2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Defining an event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.1 What is an event? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.2 Types of events . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.2.3 Useful event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.3.1 Useful event in Politics . . . . . . . . . . . . . . . . . . . . 9
2.2.3.2 Useful event in Health . . . . . . . . . . . . . . . . . . . . 9
2.2.3.3 Useful event in Disaster . . . . . . . . . . . . . . . . . . . 9
2.2.3.4 Useful event in Social sciences . . . . . . . . . . . . . . . . 10
2.2.3.5 Useful event in Sport . . . . . . . . . . . . . . . . . . . . . 10
2.2.4 Definition of Event detection . . . . . . . . . . . . . . . . . . . . . . 10
2.2.5 Event detection methods . . . . . . . . . . . . . . . . . . . . . . . 11
2.3 Event Detection on OSM . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.1 Definition of social media . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.2 Social media data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4 Event Detection on Twitter . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4.1 Presentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.4.2 Functionalities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.4.3 Twitter usage statistics . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.4.4 Challenges in using Twitter as a source of information . . . . . . . . 14
2.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3 Techniques and Methods 16
3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2 Similarities based methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.1 Texts similarities . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.2 Measures of Similarity . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.1 Cosine Similarity . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.2 Jaccard Coefficient . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.3 Dice Coefficient . . . . . . . . . . . . . . . . . . . . . . . . 19
3.2.2.4 Overlap Coefficient . . . . . . . . . . . . . . . . . . . . . . 20
3.2.2.5 Euclidean distance(L2) . . . . . . . . . . . . . . . . . . . . 20
3.2.2.6 Manhattan distance(L1) . . . . . . . . . . . . . . . . . . . 20
3.3 Machine Learning based methods . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.1 Supervised learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.1.1 Neural Networks (ANN) . . . . . . . . . . . . . . . . . . . 21
3.3.1.2 Recurrent Neural Network (RNN) . . . . . . . . . . . . . . 22
3.3.2 Unsupervised learning . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.2.1 K-means . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.2.2 Agglomerative clustering . . . . . . . . . . . . . . . . . . . 23
3.3.2.3 K-Medoids . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.4 Deep Learning-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.4.1 Long short-term memory (LSTM) . . . . . . . . . . . . . . . . . . . 24
3.4.2 Gated Recurrent Neural Network(GRU) . . . . . . . . . . . . . . . 25
3.5 Word embedding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
3.6 Transformers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
3.6.1 Transformer model . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.6.2 Pretrained Models: BERT . . . . . . . . . . . . . . . . . . . . . . . 28
3.7 Functions of Activation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
3.7.1 The function of Linear Activation . . . . . . . . . . . . . . . . . . . 29
3.7.2 Non-Linear Function of Activation . . . . . . . . . . . . . . . . . . 30
3.7.2.1 Sigmoid Function . . . . . . . . . . . . . . . . . . . . . . 30
3.7.2.2 Tanh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
3.7.2.3 Sigmoid and Tanh comparison . . . . . . . . . . . . . . . . 32
3.7.2.4 ReLU (Rectified Linear Unit) Function . . . . . . . . . . . 32
3.7.2.5 Exponential Linear Units(ELU) . . . . . . . . . . . . . . . 33
3.7.2.6 Softmax Function . . . . . . . . . . . . . . . . . . . . . . . 34
3.7.2.7 SoftPlus Function . . . . . . . . . . . . . . . . . . . . . . 34
3.8 Evaluation metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.8.1 Confusion Matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.8.2 Measuring Performance . . . . . . . . . . . . . . . . . . . . . . . . . 36
3.9 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
4 Literature Review 41
4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2 Event Detection Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1 Datasets from Twitter . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1.1 Event collections . . . . . . . . . . . . . . . . . . . . . . . 42
4.2.1.2 EveTAR collections . . . . . . . . . . . . . . . . . . . . . . 42
4.2.2 Datasets from the general domain . . . . . . . . . . . . . . . . . . . 43
4.3 Event Detection techniques . . . . . . . . . . . . . . . . . . . . . . . . . . 43
4.3.1 Specified Event Detection(SED) . . . . . . . . . . . . . . . . . . . . 43
4.3.2 Unspecified Event Detection(UED) . . . . . . . . . . . . . . . . . . 43
4.4 Approaches for event detection . . . . . . . . . . . . . . . . . . . . . . . . 44
4.5 Different techniques and methods proposed for event detection and classification
on OSM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
4.6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
5 Frameworks and Experimentations 54
5.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
5.2 Building a Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
5.2.1 Collecting Tweets for the Dataset . . . . . . . . . . . . . . . . . . . 55
5.2.2 Adapting Datasets for Event Detection and Classification . . . . . . 57
5.2.3 Dataset Statistics . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
5.3 AI-based Models for Event Detection and Classification . . . . . . . . . . . 59
5.3.1 Supervised Learning Based Models . . . . . . . . . . . . . . . . . . 59
5.3.1.1 BERT+LSTM model for events classification . . . . . . . 60
5.3.1.2 LSTM based model for Multi-classifaction . . . . . . . . . 68
5.3.1.3 Hybrid Similarity and BERT-Based Models for Event Detection
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83
5.3.2 Unsupervised based Models . . . . . . . . . . . . . . . . . . . . . . 92
5.3.2.1 Clustering and labeling Algorithm for English Dataset . . 94
5.3.2.2 Clustering and labeling Algorithm for Arabic Dataset . . . 95
5.3.2.3 Experiments and evaluations . . . . . . . . . . . . . . . . 96
5.3.2.4 Clustering algorithms for English tweets . . . . . . . . . . 96
5.3.2.5 Clustering performance of DistilBERT and TF-IDF . . . . 100
5.3.2.6 Clustering algorithms for Arabic tweets . . . . . . . . . . 100
5.3.2.7 Analysis result According to the Number of Clusters . . . 103
5.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 106
6 Conclusions and Future Works 107
6.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107
6.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109
|
| Côte titre : |
DI/0088 |
|
Ajouter le résultat dans votre panier Affiner la recherche
