Marco Büchler, S. Riegert, Federico Alpi, Francesca Cadeddu
Data in and for religion is arguably as old as humanity. Religious significance has been attached to an immense variety of artifacts and documents, often in written form, in nearly all spoken and written languages over the past millennia. The rise of the digital age gives to the scholar in religious studies the opportunity to build research over a much wider array of data than ever before; institutions which have data repositories (such as libraries, museums, universities, etc.) similarly have the chance to make their collections available to a larger community. On the other hand, however, there is a serious risk that a considerable amount of data gets lost during the "Digital transition". This paper presents the approach of the RESILIENCE Research Infrastructure in dealing with the issue of big data and data loss within the field of religious studies.
{"title":"Towards big religious data: RESILIENCE research infrastructure for data on religion in the digital age","authors":"Marco Büchler, S. Riegert, Federico Alpi, Francesca Cadeddu","doi":"10.1145/3423603.3424007","DOIUrl":"https://doi.org/10.1145/3423603.3424007","url":null,"abstract":"Data in and for religion is arguably as old as humanity. Religious significance has been attached to an immense variety of artifacts and documents, often in written form, in nearly all spoken and written languages over the past millennia. The rise of the digital age gives to the scholar in religious studies the opportunity to build research over a much wider array of data than ever before; institutions which have data repositories (such as libraries, museums, universities, etc.) similarly have the chance to make their collections available to a larger community. On the other hand, however, there is a serious risk that a considerable amount of data gets lost during the \"Digital transition\". This paper presents the approach of the RESILIENCE Research Infrastructure in dealing with the issue of big data and data loss within the field of religious studies.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"26 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132394167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Darmont, Cécile Favre, Sabine Loudcher, C. Noûs
Traditional data in Digital Humanities projects bear various formats (structured, semi-structured, textual) and need substantial transformations (encoding and tagging, stemming, lemmatization, etc.) to be managed and analyzed. To fully master this process, we propose the use of data lakes as a solution to data siloing and big data variety problems. We describe data lake projects we currently run in close collaboration with researchers in humanities and social sciences and discuss the lessons learned running these projects.
{"title":"Data lakes for digital humanities","authors":"J. Darmont, Cécile Favre, Sabine Loudcher, C. Noûs","doi":"10.1145/3423603.3424004","DOIUrl":"https://doi.org/10.1145/3423603.3424004","url":null,"abstract":"Traditional data in Digital Humanities projects bear various formats (structured, semi-structured, textual) and need substantial transformations (encoding and tagging, stemming, lemmatization, etc.) to be managed and analyzed. To fully master this process, we propose the use of data lakes as a solution to data siloing and big data variety problems. We describe data lake projects we currently run in close collaboration with researchers in humanities and social sciences and discuss the lessons learned running these projects.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Orélie Desfriches-Doria, J. Debaz, Waldir Lisboa Rocha Filho
With interdisciplinary contexts and various epistemic points of view, Digital Humanities implies to take into account social dimensions in the production of tools, methods and archive processes. From a pragmatic point of view, Digital Humanities activities involve complex interpretative processes, linking human (individual and collective understanding) and algorithmic computation spaces. This articulation is emphasized in Prospéro software, but still has to support community dialog processes, which can be understood according to vocabulary alignment paradigm or socio-anthropological usage of language paradigm. In order to do so, we give some exploratory guidelines to express and historicize taxonomic processes and define the conditions by which algorithms could support such developments.
{"title":"Interoperability and discursive process about categories","authors":"Orélie Desfriches-Doria, J. Debaz, Waldir Lisboa Rocha Filho","doi":"10.1145/3423603.3424005","DOIUrl":"https://doi.org/10.1145/3423603.3424005","url":null,"abstract":"With interdisciplinary contexts and various epistemic points of view, Digital Humanities implies to take into account social dimensions in the production of tools, methods and archive processes. From a pragmatic point of view, Digital Humanities activities involve complex interpretative processes, linking human (individual and collective understanding) and algorithmic computation spaces. This articulation is emphasized in Prospéro software, but still has to support community dialog processes, which can be understood according to vocabulary alignment paradigm or socio-anthropological usage of language paradigm. In order to do so, we give some exploratory guidelines to express and historicize taxonomic processes and define the conditions by which algorithms could support such developments.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"442 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125765060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Ac 29 register of the Waldensian cantonal archives is one of the most famous documents of the repression of witchcraft. It covers about thirty witchcraft prosecutions, which have been studied for more than a hundred years. After having been edited, translated and commented on, a new stage in the life of this collection has begun. Indeed, it has been entirely tagged according to the recommendations of the TEI and indexed to an online database, which is now accessible via the Sources du droit Suisse website.
{"title":"From register to digital: a 100-years study of witchhunts around Ac 29","authors":"Gwendolin Ortega","doi":"10.1145/3423603.3424006","DOIUrl":"https://doi.org/10.1145/3423603.3424006","url":null,"abstract":"The Ac 29 register of the Waldensian cantonal archives is one of the most famous documents of the repression of witchcraft. It covers about thirty witchcraft prosecutions, which have been studied for more than a hundred years. After having been edited, translated and commented on, a new stage in the life of this collection has begun. Indeed, it has been entirely tagged according to the recommendations of the TEI and indexed to an online database, which is now accessible via the Sources du droit Suisse website.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123334617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Information is one of the most important factors in business success, hence the importance of the Business Intelligence (BI) domain in order to simplify the decision making and make it more relevant. Decisional systems have been used for several years to help decision-makers access, analyze and extract value from the data that their organisation accumulated through the years. The success gained by these types of systems caused the establishment of a well-known architecture and development chain, and the proliferation of tools and methodologies that have proven their value. Nonetheless, in some use cases, the classical decisional architecture shows some shortcomings. In fact, the traditional storage and processing models in Business Intelligence systems are not sufficient anymore when confronted with data that becomes more and more massive, varied and with a high velocity. This is where Big Data solutions can be of great use. In fact, these solutions have proven their efficiency when dealing with enormous constantly increasing amounts of data with a changing schema. Our goal in this article is to show the various manners to integrate big data solutions into the decisional world, and to help architects choose which architecture corresponds better to their needs, by taking into consideration the environmental, technical and functional constraints they are faced with.
{"title":"Decisional architectures from business intelligence to big data: challenges and opportunities","authors":"M. Aissa, Lilia Sfaxi, R. Robbana","doi":"10.1145/3423603.3424049","DOIUrl":"https://doi.org/10.1145/3423603.3424049","url":null,"abstract":"Information is one of the most important factors in business success, hence the importance of the Business Intelligence (BI) domain in order to simplify the decision making and make it more relevant. Decisional systems have been used for several years to help decision-makers access, analyze and extract value from the data that their organisation accumulated through the years. The success gained by these types of systems caused the establishment of a well-known architecture and development chain, and the proliferation of tools and methodologies that have proven their value. Nonetheless, in some use cases, the classical decisional architecture shows some shortcomings. In fact, the traditional storage and processing models in Business Intelligence systems are not sufficient anymore when confronted with data that becomes more and more massive, varied and with a high velocity. This is where Big Data solutions can be of great use. In fact, these solutions have proven their efficiency when dealing with enormous constantly increasing amounts of data with a changing schema. Our goal in this article is to show the various manners to integrate big data solutions into the decisional world, and to help architects choose which architecture corresponds better to their needs, by taking into consideration the environmental, technical and functional constraints they are faced with.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115309262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Hafaiedh, Mouhib Ben Rhouma, Fahd Chargui, Yassine Haouas, A. Kerkeni
Digital Advertising and promotional e-campaigns have been a basic pillar of marketing. One of the main challenges marketers face nowadays is about associating the right promotion to the right customer. Making the product-customer assignment accurate is crucial to satisfy customer needs. However, manually analyzing qualitative data for the purpose of defining the right target audience is exhausting and time consuming, especially when the number of costumers is high. In this paper, our aim is to automatically assign personalized campaigns that match specific customer desire, therefore making promotional campaigns consistent with their interests. Automating the process of assigning the right promotion to the right customer according to its specific needs is appealing as customers often show little to no interest in random ads. Our solution, referred to as "AdRobot", aims at overcoming these challenges by gathering complex data and insights into the target audience using data collected from conversations via the designed chatbot. Our strategy consists of performing fine-grained audience classification by segmenting profiles based on some profiling and conversational constraints, so that the audience is matched with the right promotional campaign. In order to achieve this goal, we propose an algorithm that investigates profiling and conversational data collected along with the customers' intents using artificial intelligence heuristics. Results show that "AdRobot" accurately matches promotional campaigns with the right customers according to their needs.
{"title":"AdRobot","authors":"K. Hafaiedh, Mouhib Ben Rhouma, Fahd Chargui, Yassine Haouas, A. Kerkeni","doi":"10.1145/3423603.3424052","DOIUrl":"https://doi.org/10.1145/3423603.3424052","url":null,"abstract":"Digital Advertising and promotional e-campaigns have been a basic pillar of marketing. One of the main challenges marketers face nowadays is about associating the right promotion to the right customer. Making the product-customer assignment accurate is crucial to satisfy customer needs. However, manually analyzing qualitative data for the purpose of defining the right target audience is exhausting and time consuming, especially when the number of costumers is high. In this paper, our aim is to automatically assign personalized campaigns that match specific customer desire, therefore making promotional campaigns consistent with their interests. Automating the process of assigning the right promotion to the right customer according to its specific needs is appealing as customers often show little to no interest in random ads. Our solution, referred to as \"AdRobot\", aims at overcoming these challenges by gathering complex data and insights into the target audience using data collected from conversations via the designed chatbot. Our strategy consists of performing fine-grained audience classification by segmenting profiles based on some profiling and conversational constraints, so that the audience is matched with the right promotional campaign. In order to achieve this goal, we propose an algorithm that investigates profiling and conversational data collected along with the customers' intents using artificial intelligence heuristics. Results show that \"AdRobot\" accurately matches promotional campaigns with the right customers according to their needs.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121298174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The production of audiovisual content continues to increase, and mainly the content intended for children such as the animated video. However, children are unable to judge the quality, relevance and essentially the adequacy of videos to their ages. In this case, the problem is that many videos can have a negative impact on the psychology and the emotional state of children. Our aim in this work is to identify if an animated video can have a negative impact or not in order to develop a recommendation system. The desired system allows to avoid animated movies causing negative impacts for children. For this, we use a chromatic approach. We propose multi-level descriptors, based on color features, in the judging process. The results of the experimental study of the proposed approach prove its performance and consequently the importance of chromatic features as pertinent features for a recommendation system that aims to reduce the emotional and psychological impacts of children movies and avoid them.
{"title":"Towards a recommendation system for children's animated movies based on chromatic features","authors":"M. Frikha, Tarek Zlitni, N. Bouassida","doi":"10.1145/3423603.3424058","DOIUrl":"https://doi.org/10.1145/3423603.3424058","url":null,"abstract":"The production of audiovisual content continues to increase, and mainly the content intended for children such as the animated video. However, children are unable to judge the quality, relevance and essentially the adequacy of videos to their ages. In this case, the problem is that many videos can have a negative impact on the psychology and the emotional state of children. Our aim in this work is to identify if an animated video can have a negative impact or not in order to develop a recommendation system. The desired system allows to avoid animated movies causing negative impacts for children. For this, we use a chromatic approach. We propose multi-level descriptors, based on color features, in the judging process. The results of the experimental study of the proposed approach prove its performance and consequently the importance of chromatic features as pertinent features for a recommendation system that aims to reduce the emotional and psychological impacts of children movies and avoid them.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128809090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intrusion detection system (IDS) is one of the best solutions protecting against the attacks and anomalies. Behaviour based IDS is one type of IDS that is the most subject draining the interest of most research works in the cyber-security field. The main problems treated are accuracy and false positive rate. Distribution of the detection process is one solution for those problems. The distribution consists of implementing an agent based IDS where each and every agent has a goal to achieve so the intrusion detection process can be completed with the best results through the multi agent system features including the communication, negotiation, ... . The adapted solution in our model proposed is a distributed Intelligent agent based intrusion detection system using convolutional and recurrent neural networks for the training and attack prevention.
{"title":"A distributed intelligent agent based intrusion detection system using deep learning algorithms","authors":"Sami Mezghani, F. Ktata","doi":"10.1145/3423603.3424054","DOIUrl":"https://doi.org/10.1145/3423603.3424054","url":null,"abstract":"Intrusion detection system (IDS) is one of the best solutions protecting against the attacks and anomalies. Behaviour based IDS is one type of IDS that is the most subject draining the interest of most research works in the cyber-security field. The main problems treated are accuracy and false positive rate. Distribution of the detection process is one solution for those problems. The distribution consists of implementing an agent based IDS where each and every agent has a goal to achieve so the intrusion detection process can be completed with the best results through the multi agent system features including the communication, negotiation, ... . The adapted solution in our model proposed is a distributed Intelligent agent based intrusion detection system using convolutional and recurrent neural networks for the training and attack prevention.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124623202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of big corpora of various periods, it becomes crucial to standardise linguistic annotation (e.g. lemmas, POS tags, morphological annotation) to increase the interoperability of the data produced, despite diachronic variations. In the present paper, we describe both methodologically (by proposing annotation principles) and technically (by creating the required training data and the relevant models) the production of a linguistic tagger for (early) modern French (16-18th c.), taking as much as possible into account already existing standards for contemporary and, especially, medieval French.
{"title":"Standardizing linguistic data: method and tools for annotating (pre-orthographic) French","authors":"Simon Gabay, Thibault Clérice, Jean-Baptiste Camps, Jean-Baptiste Tanguy, Matthias Gille Levenson","doi":"10.1145/3423603.3423996","DOIUrl":"https://doi.org/10.1145/3423603.3423996","url":null,"abstract":"With the development of big corpora of various periods, it becomes crucial to standardise linguistic annotation (e.g. lemmas, POS tags, morphological annotation) to increase the interoperability of the data produced, despite diachronic variations. In the present paper, we describe both methodologically (by proposing annotation principles) and technically (by creating the required training data and the relevant models) the production of a linguistic tagger for (early) modern French (16-18th c.), taking as much as possible into account already existing standards for contemporary and, especially, medieval French.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125032680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Within the Cloud Computing context, the placement of massive data used by scientific workflows environment appears to be costly in terms of energy consumption and data transfer time. Indeed, due to the large size of consumed and generated datasets of scientific workflows tasks, the data placement problem becomes more challenging task. This problem is considered as NP-Hard problem. Ensuring an optimal mapping of data to Cloud Storage Services at a reasonable time turns out to be necessary. Many task-level approaches have been hence proposed while considering shared datasets within individual workflows to reduce data transfer cost, which is not efficient enough for the situation of multiple workflows. In the same perspective, taking into account the fixed datasets still an important issue. In the present paper, cooperative agents and Formal Analysis Concepts (FCA) based-data placement strategy for workflow-level data-intensive workflows is proposed. The proposed approach deals with three main concerns: i) treating multiple workflows simultaneously, ii) considering all types of data, specifically, fixed datasets, and iii) reducing the execution time of the data placement algorithm based on a set of cooperative intelligent agents. Experimental results show that the distribution of the proposed data placement strategy among a set of cooperative agents and the FCA approach can be more cost-effective than its task-level counterpart. Eventually, the proposed strategy proves to reduce the execution time during the execution of the tasks of multiple workflows.
{"title":"A cooperative agents-based workflow-level distributed data placement strategy for scientific cloud workflows","authors":"Rihab Derouiche, Zaki Brahmi","doi":"10.1145/3423603.3424009","DOIUrl":"https://doi.org/10.1145/3423603.3424009","url":null,"abstract":"Within the Cloud Computing context, the placement of massive data used by scientific workflows environment appears to be costly in terms of energy consumption and data transfer time. Indeed, due to the large size of consumed and generated datasets of scientific workflows tasks, the data placement problem becomes more challenging task. This problem is considered as NP-Hard problem. Ensuring an optimal mapping of data to Cloud Storage Services at a reasonable time turns out to be necessary. Many task-level approaches have been hence proposed while considering shared datasets within individual workflows to reduce data transfer cost, which is not efficient enough for the situation of multiple workflows. In the same perspective, taking into account the fixed datasets still an important issue. In the present paper, cooperative agents and Formal Analysis Concepts (FCA) based-data placement strategy for workflow-level data-intensive workflows is proposed. The proposed approach deals with three main concerns: i) treating multiple workflows simultaneously, ii) considering all types of data, specifically, fixed datasets, and iii) reducing the execution time of the data placement algorithm based on a set of cooperative intelligent agents. Experimental results show that the distribution of the proposed data placement strategy among a set of cooperative agents and the FCA approach can be more cost-effective than its task-level counterpart. Eventually, the proposed strategy proves to reduce the execution time during the execution of the tasks of multiple workflows.","PeriodicalId":387247,"journal":{"name":"Proceedings of the 2nd International Conference on Digital Tools & Uses Congress","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130346419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：