Searcharxiv⌕ Search

arXiv subjects

Jérôme Darmont

Publications and source records attributed to Jérôme Darmont.

At least 19 recordsLinked to original sources
arXiv2026

Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case

Data lakes rely on metadata to remain usable, yet this meta data is often limited or weakly informative for column relationship discovery, especially in ERP-derived datasets with coded or abbreviated schema labels. We propose ColRel, a two-stage method that builds column embeddings from metadata and data available at ingestion time. In difficult cases, such as coded schemata, business dictionaries help better interpret column names and support the generation of short natural-language descriptions used in the second stage. Experiments on public benchmarks and an industrial ERP dataset show that ColRel is particularly effective in semantically related, weak-signal settings.

cs.AI↗
arXiv2025

Experiversum: an Ecosystem for Curating and Enhancing Data-Driven Experimental Science

This paper introduces Experiversum, a lakehouse-based ecosystem that supports the curation, documentation and reproducibility of exploratory experiments. Experiversum enables structured research through iterative data cycles, while capturing metadata and collaborative decisions. Demonstrated through case studies in Earth, Life and Political Sciences, Experiversum promotes transparent workflows and multi-perspective result interpretation. Experiversum bridges exploratory and reproducible research, encouraging accountable and robust data-driven practices across disciplines.

cs.DB↗
arXiv2024

Dataversifying Natural Sciences: Pioneering a Data Lake Architecture for Curated Data-Centric Experiments in Life \& Earth Sciences

This vision paper introduces a pioneering data lake architecture designed to meet Life \& Earth sciences' burgeoning data management needs. As the data landscape evolves, the imperative to navigate and maximize scientific opportunities has never been greater. Our vision paper outlines a strategic approach to unify and integrate diverse datasets, aiming to cultivate a collaborative space conducive to scientific discovery.The core of the design and construction of a data lake is the development of formal and semi-automatic tools, enabling the meticulous curation of quantitative and qualitative data from experiments. Our unique ''research-in-the-loop'' methodology ensures that scientists across various disciplines are integrally involved in the curation process, combining automated, mathematical, and manual tasks to address complex problems, from seismic detection to biodiversity studies. By fostering reproducibility and applicability of research, our approach enhances the integrity and impact of scientific experiments. This initiative is set to improve data management practices, strengthening the capacity of Life \& Earth sciences to solve some of our time's most critical environmental and biological challenges.

cs.DB↗
arXiv2023

An Ontology-based Collaborative Business Intelligence Framework

Business Intelligence constitutes a set of methodologies and tools aiming at querying, reporting, on-line analytic processing (OLAP), generating alerts, performing business analytics, etc. When in need to perform these tasks collectively by different collaborators, we need a Collaborative Business Intelligence (CBI) platform. CBI plays a significant role in targeting a common goal among various companies, but it requires them to connect, organize and coordinate with each other to share opportunities, respecting their own autonomy and heterogeneity. This paper presents a CBI platform that hat democratizes data by allowing BI users to easily connect, share and visualize data among collaborators, obtain actionable answers by collaborative analysis, investigate and make collaborative decisions, and also store the analyses along graphical diagrams and charts in a collaborative ontology knowledge base. Our CBI framework supports and assists information sharing, collaborative decision-making and annotation management beyond the boundaries of individuals and enterprises.

cs.DB↗
arXiv2023

A Reference Model for Collaborative Business Intelligence Virtual Assistants

Collaborative Business Analysis (CBA) is a methodology that involves bringing together different stakeholders, including business users, analysts, and technical specialists, to collaboratively analyze data and gain insights into business operations. The primary objective of CBA is to encourage knowledge sharing and collaboration between the different groups involved in business analysis, as this can lead to a more comprehensive understanding of the data and better decision-making. CBA typically involves a range of activities, including data gathering and analysis, brainstorming, problem-solving, decision-making and knowledge sharing. These activities may take place through various channels, such as in-person meetings, virtual collaboration tools or online forums. This paper deals with virtual collaboration tools as an important part of Business Intelligence (BI) platform. Collaborative Business Intelligence (CBI) tools are becoming more user-friendly, accessible, and flexible, allowing users to customize their experience and adapt to their specific needs. The goal of a virtual assistant is to make data exploration more accessible to a wider range of users and to reduce the time and effort required for data analysis. It describes the unified business intelligence semantic model, coupled with a data warehouse and collaborative unit to employ data mining technology. Moreover, we propose a virtual assistant for CBI and a reference model of virtual tools for CBI, which consists of three components: conversational, data exploration and recommendation agents. We believe that the allocation of these three functional tasks allows you to structure the CBI issue and apply relevant and productive models for human-like dialogue, text-to-command transferring, and recommendations simultaneously. The complex approach based on these three points gives the basis for virtual tool for collaboration. CBI encourages people, processes, and technology to enable everyone sharing and leveraging collective expertise, knowledge and data to gain valuable insights for making better decisions. This allows to respond more quickly and effectively to changes in the market or internal operations and improve the progress.

cs.HC↗
arXiv2023

Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning

The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR's performance.

cs.CV↗
arXiv2022

The Collaborative Business Intelligence Ontology (CBIOnt)

In the current era, many disciplines are seen devoted towards ontology development for their domains with the intention of creating, disseminating and managing resource descriptions of their domain knowledge into machine understandable and processable manner. Ontology construction is a difficult group activity that involves many people with the different expertise. Generally, domain experts are not familiar with the ontology implementation environments and implementation experts do not have all the domain knowledge. We have designed Collaborative Business Intelligence Ontology (CBIOnt) for BI4People project. In this paper, we present CBIOnt that is OWL 2 DL ontology for the description of collaborative session between different collaborators working together on the business intelligent platform. As the collaborative session between various collaborators belongs to some collaborative form, phase and research aspect, therefore CBIOnt captures this knowledge along with the collaborative session content (comments, questions, answers, etc.) so that one can inference various types of information stored on ontologies when required. In addition, it stores the location and temporal-spatial information about the collaboration held between collaborators. We believe CBIOnt serves as a formal framework for dealing with the collaborative session taken place among collaborators on the semantic Web.

cs.DB↗
arXiv2022

Dimensional Data KNN-Based Imputation

Data Warehouses (DWs) are core components of Business Intelligence (BI). Missing data in DWs have a great impact on data analyses. Therefore, missing data need to be completed. Unlike other existing data imputation methods mainly adapted for facts, we propose a new imputation method for dimensions. This method contains two steps: 1) a hierarchical imputation and 2) a k-nearest neighbors (KNN) based imputation. Our solution has the advantage of taking into account the DW structure and dependency constraints. Experimental assessments validate our method in terms of effectiveness and efficiency.

cs.DB↗
arXiv2021

Calling to CNN-LSTM for Rumor Detection: A Deep Multi-channel Model for Message Veracity Classification in Microblogs

Reputed by their low-cost, easy-access, real-time and valuable information, social media also wildly spread unverified or fake news. Rumors can notably cause severe damage on individuals and the society. Therefore, rumor detection on social media has recently attracted tremendous attention. Most rumor detection approaches focus on rumor feature analysis and social features, i.e., metadata in social media. Unfortunately, these features are data-specific and may not always be available, e.g., when the rumor has just popped up and not yet propagated. In contrast, post contents (including images or videos) play an important role and can indicate the diffusion purpose of a rumor. Furthermore, rumor classification is also closely related to opinion mining and sentiment analysis. Yet, to the best of our knowledge, exploiting images and sentiments is little investigated.Considering the available multimodal features from microblogs, notably, we propose in this paper an end-to-end model called deepMONITOR that is based on deep neural networks and allows quite accurate automated rumor verification, by utilizing all three characteristics: post textual and image contents, as well as sentiment. deepMONITOR concatenates image features with the joint text and sentiment features to produce a reliable, fused classification. We conduct extensive experiments on two large-scale, real-world datasets. The results show that deepMONITOR achieves a higher accuracy than state-of-the-art methods.

cs.CL↗
arXiv2021

Internal Data Imputation in Data Warehouse Dimensions

Missing values occur commonly in the multidimensional data warehouses. They may generate problems of usefulness of data since the analysis performed on a multidimensional data warehouse is through different dimensions with hierarchies where we can roll up or drill down to the different parameters of analysis. Therefore, it's essential to complete these missing values in order to carry out a better analysis. There are existing data imputation methods which are suitable for numeric data, so they can be applied for fact tables but not for dimension tables. Some other data imputation methods need extra time and effort costs. As consequence, we propose in this article an internal data imputation method for multidimensional data warehouse based on the existing data and considering the intra-dimension and inter-dimension relationships.

cs.DB↗
arXiv2021

Benchmarking Data Lakes Featuring Structured and Unstructured Data with DLBench

In the last few years, the concept of data lake has become trendy for data storage and analysis. Thus, several design alternatives have been proposed to build data lake systems. However, these proposals are difficult to evaluate as there are no commonly shared criteria for comparing data lake systems. Thus, we introduce DLBench, a benchmark to evaluate and compare data lake implementations that support textual and/or tabular contents. More concretely, we propose a data model made of both textual and raw tabular documents, a workload model composed of a set of various tasks, as well as a set of performance-based metrics, all relevant to the context of data lakes. As a proof of concept, we use DLBench to evaluate an open source data lake system we previously developed.

cs.DB↗
arXiv2021

MONITOR: A Multimodal Fusion Framework to Assess Message Veracity in Social Networks

Users of social networks tend to post and share content with little restraint. Hence, rumors and fake news can quickly spread on a huge scale. This may pose a threat to the credibility of social media and can cause serious consequences in real life. Therefore, the task of rumor detection and verification has become extremely important. Assessing the veracity of a social media message (e.g., by fact checkers) involves analyzing the text of the message, its context and any multimedia attachment. This is a very time-consuming task that can be much helped by machine learning. In the literature, most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. In this paper, we second the hypothesis that exploiting all of the components of a social media post enhances the accuracy of veracity detection. To further the state of the art, we first propose using a set of advanced image features that are inspired from the field of image quality assessment, which effectively contributes to rumor detection. These metrics are good indicators for the detection of fake images, even for those generated by advanced techniques like generative adversarial networks (GANs). Then, we introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features (i.e., text, social context, and image features) by supervised machine learning. Such algorithms provide interpretability and explainability in the decisions taken, which we believe is particularly important in the context of rumor verification. Experimental results show that MONITOR can detect rumors with an accuracy of 96% and 89% on the MediaEval benchmark and the FakeNewsNet dataset, respectively. These results are significantly better than those of state-of-the-art machine learning baselines.

cs.SI↗
arXiv2021

Joint Management and Analysis of Textual Documents and Tabular Data within the AUDAL Data Lake

In 2010, the concept of data lake emerged as an alternative to data warehouses for big data management. Data lakes follow a schema-on-read approach to provide rich and flexible analyses. However, although trendy in both the industry and academia, the concept of data lake is still maturing, and there are still few methodological approaches to data lake design. Thus, we introduce a new approach to design a data lake and propose an extensive metadata system to activate richer features than those usually supported in data lake approaches. We implement our approach in the AUDAL data lake, where we jointly exploit both textual documents and tabular data, in contrast with structured and/or semi-structured data typically processed in data lakes from the literature. Furthermore, we also innovate by leveraging metadata to activate both data retrieval and content analysis, including Text-OLAP and SQL querying. Finally, we show the feasibility of our approach using a real-word use case on the one hand, and a benchmark on the other hand.

cs.DB↗
arXiv2021

TextBenDS: a generic Textual data Benchmark for Distributed Systems

Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, computation errors are introduced when analyzing only subsets of the dataset. Therefore, in a Big Data context, it is crucial to lower the runtime of computing weighting schemes, without hindering the analysis process and the accuracy of the machine learning algorithms. To address this requirement for the task of top-k keywords and documents, it is customary to design benchmarks that compare weighting schemes within various configurations of distributed frameworks and database management systems. Thus, we propose a generic document-oriented benchmark for storing textual data and constructing weighting schemes (TextBenDS). Our benchmark offers a generic data model designed with a multidimensional approach for storing text documents. We also propose using aggregation queries with various complexities and selectivities for constructing term weighting schemes, that are utilized in extracting top-k keywords and documents. We evaluate the computing performance of the queries on several distributed environments set within the Apache Hadoop ecosystem. Our experimental results provide interesting insights. As an example, MongoDB proves to have the best overall performance, while Spark's execution time remains almost the same, regardless of the weighting schemes.

cs.DB↗
arXiv2021

An Automatic Schema-Instance Approach for Merging Multidimensional Data Warehouses

Using data warehouses to analyse multidimensional data is a significant task in company decision-making.The data warehouse merging process is composed of two steps: matching multidimensional components and then merging them. Current approaches do not take all the particularities of multidimensional data warehouses into account, e.g., only merging schemata, but not instances; or not exploiting hierarchies nor fact tables. Thus, in this paper, we propose an automatic merging approach for star schema-modeled data warehouses that works at both the schema and instance levels. We also provide algorithms for merging hierarchies, dimensions and facts. Eventually, we implement our merging algorithms and validate them with the use of both synthetic and benchmark datasets.

cs.DB↗
arXiv2021

On data lake architectures and metadata management

Over the past two decades, we have witnessed an exponential increase of data production in the world. So-called big data generally come from transactional systems, and even more so from the Internet of Things and social media. They are mainly characterized by volume, velocity, variety and veracity issues. Big data-related issues strongly challenge traditional data management and analysis systems. The concept of data lake was introduced to address them. A data lake is a large, raw data repository that stores and manages all company data bearing any format. However, the data lake concept remains ambiguous or fuzzy for many researchers and practitioners, who often confuse it with the Hadoop technology. Thus, we provide in this paper a comprehensive state of the art of the different approaches to data lake design. We particularly focus on data lake architectures and metadata management, which are key issues in successful data lakes. We also discuss the pros and cons of data lakes and their design alternatives.

cs.DB↗
arXiv2021

ArchaeoDAL: A Data Lake for Archaeological Data Management and Analytics

With new emerging technologies, such as satellites and drones, archaeologists collect data over large areas. However, it becomes difficult to process such data in time. Archaeological data also have many different formats (images, texts, sensor data) and can be structured, semi-structured and unstructured. Such variety makes data difficult to collect, store, manage, search and analyze effectively. A few approaches have been proposed, but none of them covers the full data lifecycle nor provides an efficient data management system. Hence, we propose the use of a data lake to provide centralized data stores to host heterogeneous data, as well as tools for data quality checking, cleaning, transformation, and analysis. In this paper, we propose a generic, flexible and complete data lake architecture. Our metadata management system exploits goldMEDAL, which is the most complete metadata model currently available. Finally, we detail the concrete implementation of this architecture dedicated to an archaeological project.

cs.DB↗