Feature engineering is a critical yet often manual step in building effective machine learning models. While automated machine learning (AutoML) has streamlined many aspects of model development, the generation of high-quality, interpretable features remains a key bottleneck, requiring case-by-case domain knowledge and significant effort. This challenge highlights the importance of automated feature engineering (AutoFE) as a critical component within AutoML pipeline. To address this, we recently proposed SMART, a novel AutoFE approach that combines knowledge graph reasoning and deep reinforcement learning to guide the generation of interpretable features. In this demonstration, we introduce KnowFE, a web-based AutoFE platform powered by SMART. KnowFE enables users to generate high-quality, human-understandable features without writing any code, striking a balance between explainability and predictive performance. With a user-friendly interface, it empowers data practitioners to efficiently enhance machine learning workflows across diverse domains. A video demonstration is available at https://www.KnowFE.com .

Feature engineering stands as a pivotal step in enhancing the performance of machine learning (ML) models, particularly with tabular data. However, traditional feature engineering methods are often time-consuming and requires case-by-case domain knowledge. In addition, as ML systems become more common, interpretability becomes increasingly important, especially among domain experts. To this end, we propose ReaGen, an automated feature engineering (AutoFE) approach that combines knowledge graphs (KGs) with large language models (LLMs) to generate interpretable features. ReaGen begins by symbolic REAsoning over the KG to extract relevant information based on datasets description. Then, it uses an LLM to iteratively GENerate meaningful features. Finally, to overcome challenges such as hallucinations and handling long contexts typical in LLMs, our model performs logical reasoning on the KG to ensure that the generated features maintain interpretability. ReaGen provides Python code for automatic feature generation and detailed explanations of feature utility. It leverages both LLM's internal knowledge and retrieved information from KGs. Experiments on public datasets demonstrate that ReaGen significantly improves prediction accuracy while ensuring high interpretability through human-like explanations for each feature. This work highlights the potential of integrating LLMs and KGs in feature engineering, paving the way for interpretable ML models.

The security and well-being of a nation’s citizens, as well as the protection of their lives and properties, are fundamental for prosperity. Unfortunately, in recent years, we have witnessed a surge in various types of crimes such as murder, robbery, terrorism, and kidnapping. This has placed significant pressure on Law Enforcement Agencies (LEAs) to effectively prevent and detect crimes, driving them to adopt various technologies in the criminal investigation process. Among these technologies, surveillance systems have emerged as a valuable tool for monitoring human behaviors and activities, particularly in public and densely populated areas of large cities. However, video analysis in crime investigation poses significant challenges for LEAs, requiring accurate and timely detection, recognition, and tracking of objects and individuals. Addressing this issue, we present CRIMEO, a smart system designed for mining and extracting behavioral patterns from video content. CRIMEO operates in real-time and leverages an ontology-based approach to represent complex semantic events and employ video analytics. This enables LEAs to automatically detect and identify different types of crimes. CRIMEO encompasses four key phases: data collection, analysis, storage, and visualization. In the data collection phase, video data from surveillance systems is gathered and transmitted, via Apache Kafka, to the subsequent phase after the video is split into frames. The data analysis phase applies a range of video analytics techniques, including face detection and recognition, object detection, action recognition, and more, to extract behavioral patterns from the video content. These extracted patterns are then stored in the Neo4j graph database during the data storage phase. Finally, in the visualization phase, inference rules defined by LEA experts are applied to detect and visualize criminal activities. To demonstrate the effectiveness of CRIMEO, we implemented the system across multiple scenarios, showcasing its relevance in aiding LEAs in the detection of various crime types. By utilizing CRIMEO, LEAs can benefit from advanced video analysis capabilities and real-time crime detection, ultimately enhancing their ability to maintain safety and security within their jurisdictions.

In this work, we propose a Weakly Semantic-based approach for Sentiment Analysis (WSSA), a novel approach that analyzes sentiment by considering weak labels from different sources (sentiment analysis tools) and aggregates them based on features such as the consistency between sources, the semantic equivalence between documents, and experts’ domain knowledge in order to improve the sentiments analysis tools results. The aggregation is achieved using a Probabilistic Soft Logic reasoner to infer the documents’ polarity.

Sentiment analysis has received constant research attention due to its usefulness and importance in different applications. However, despite the research advances in this field, most current tools suffer in prediction quality due to the inconsistencies in their results, i.e., intra- and inter-tool inconsistencies. This demonstration proposes a system for the evaluation of sentiment analysis quality namely SA-Q. The system allows the evaluation of inconsistency in sentiment analysis tools, the resolution of the inconsistency using state-of-the-art methods and the recommendation of relevant sentiment analysis tool for any type of data set provided by the attendees. It allows the attendees to compare the tools. Moreover, we demonstrate that SA-Q evaluates the consistency of tools on two levels (intra-tool and inter-tool). Through various scenarios, we showcase the challenges of inconsistency resolution, demonstrate the usefulness of the proposed system and the recommendations that can be given to the attendees for their datasets. We demonstrate that SA-Q system has practical utility in many areas of industrial applications for better decision making. This demonstration shows promising research areas for data management, NLP, and machine learning communities by adopting and drawing inspiration from truth inference methods to create more robust tools and improve the tool's scalability.

In this paper, we present a comprehensive study that evaluates six state-of-the-art sentiment analysis tools on five public datasets, based on the quality of predictive results in the presence of semantically equivalent documents, i.e., how consistent existing tools are in predicting the polarity of documents based on paraphrased text. We observe that sentiment analysis tools exhibit intra-tool inconsistency , which is the prediction of different polarity for semantically equivalent documents by the same tool, and inter-tool inconsistency , which is the prediction of different polarity for semantically equivalent documents across different tools. We introduce a heuristic to assess the data quality of an augmented dataset and a new set of metrics to evaluate tool inconsistencies. Our results indicate that tool inconsistencies is still an open problem, and they point towards promising research directions and accuracy improvements that can be obtained if such inconsistencies are resolved.

There is an urgent need to address unhealthy dietary patterns for people. Therefore, having a high food quality is essential to health by adopting good eating habits. Furthermore, the evaluation of food quality is complex because it needs huge numbers of information related to food, for example its ingredients, the environmental conditions of food productions, the consumer state of health. Such information are scattered on multiple and non communicating systems including food producer systems, open data, medical data, etc. Applying the semantic to a very large collection of information from different data sources can highly contribute to enhance the food quality score. Hence, it will improve the individual diet/health by giving adequate nutritional recommendation and avoiding inconsistent food mixing by following set of rules.In this paper, we propose an intelligent and scalable approach to ensuring the food quality for meal healthiness query answering over big data related to food in a distributed way on a Spark ecosystem. For that, the cleaning inconsistent and contradictory big data approach is built by following the steps (1)modeling the consistency rules including inference and inconsistent rules (2) detecting inconsistency through rule evaluation on Apache Spark framework to discover the minimally subset of inconsistent data (3) cleaning the inconsistency through finding the cleaned meals for consistent query answering.

Data is often associated with uncertainty because the fusion of conflicting data sources, measurement inaccuracy, sampling discrepancy, outdated data sources. We address the problem of query answering over uncertain big data sources using Resource Description Framework (RDF) and ontologies, while computing the exact uncertainty measure of the answer. Therefore, the probability is embraced along the reasoning process when answering. the query. In this paper, we introduce a probabilistic approach for answering user queries that computes complete results by exploiting uncertain knowledge on data sources. We have designed algorithms that are ontological rules based to infer implicit data by combining saturation and query rewriting reasoning. To handle big data the algorithms are spark-based implementation.

In recent years, "Big Data" has become a new ubiquitous term. Big Data is transforming science, engineering, medicine, health-care, finance, business, and ultimately our society itself. Learning from Big Data has become a significant challenge and requires development of new types of algorithms. Most machine learning algorithms can not easily scale up to Big Data. MapReduce is a simplified programming model for processing large datasets in a distributed and parallel manner. In this paper, we present our work carried in a big data project1which is dedicated to the insurance sector. This allows us to validate our method on real-world data for insurance. We present the complete pipeline or work-flow going from data collection to visualization, passing by data fusion, data analysis, clustering, and prediction tasks. The insurance dataset is enriched with data collected from heterogeneous sources. A predictive and analysis system is proposed by combining the clustering result with decision trees. We use the topological approach, especially the SOM method, for its interest in being able to cluster and visualize the data at the same time. We make the source code of our SOM-MapReduce algorithm, written with Spark using the MapReduce paradigm, publicly available2.

We address the problem of dealing with inconsistencies in fusion of big data sources using Resource Description Framework (RDF) and ontologies. We propose a scalable approach ensuring data quality for query answering over big RDF data in a distributed way on a Spark ecosystem. In so doing, the cleaning inconsistent big RDF data approach is built on the following steps (1) modeling consistency rules to detect the inconsistency triples even if it is implicitly hidden including inference and inconsistent rules (2) detecting inconsistency through rule evaluation based on Apache Spark framework to discover the minimally sub-set of inconsistent triples (3) cleaning the inconsistency through finding the best repair for consistent query answering.

Crowdsourcing is emerging as a powerful paradigm to help perform a wide range of tedious tasks in various enterprise applications. As such applications become more complex, crowdsourcing systems often require the collaboration of several experts connected through professional/social networks and organized in various teams. For instance, a well-known car manufacturer asked fans to contribute ideas for the kinds of technologies that should be incorporated into one of its cars. For that purpose, fans needed to collaborate and form teams competing with each others to come up with the best ideas. However, once teams are formed, each one would like to provide the best solution and treat that solution as a “trade secret,” hence preventing any data leak to its competitors (i.e., the other teams). In this article, we propose a data leak--aware crowdsourcing system called SocialCrowd . We introduce a clustering algorithm that uses social relationships between crowd workers to discover all possible teams while avoiding interteam data leakage. We also define a ranking mechanism to select the “best” team configurations. Our mechanism is based on the semiring approach defined in the area of soft constraints programming. Finally, we present experiments to assess the efficiency of the proposed approach.

Matching dependencies (MDs) were recently introduced as quality rules for data cleaning and entity resolution. They are rules that specify what values should be considered duplicates, and have to be matched. Defining such quality rules on a database instance, is a very expensive and a time consuming process, and requires huge efforts to analyse the whole database. In this demo paper, we present CrowdMD, a hybrid machine-crowd system for generating MDs. It first asks the crowd to determine whether a given pair, from training sample pairs, match or not. Then, it uses data mining techniques to generate attributes constituting an MD. Using a Restaurant database, we will show how the crowders can help to generate MDs by labelling the training sample through the CrowdMD user interface and how MDs can be mined from this training set.

Web services privacy issues have been attracting more and more attention in the past years. Since the number of Web services-based business applications is increasing, the demands for privacy enhancing technologies for Web services will also be increasing in the future. In this paper, we investigate an extension of business protocols, i.e. the specification of which message exchange sequences are supported by the web service, in order to accommodate privacy aspects and time-related properties. For this purpose we introduce the notion of Timed Privacy-aware Business Protocols (TPBPs). We also discuss TPBP properties can be checked and we describe their verification process.

The demonstration addresses the problem of monitoring the compliance of privacy agreement that spells out a consumer's privacy rights and how their private information must be handled by the service provider. We present a Privacy Agreement Monitoring system, an easy-to-use, and an efficient tool for tightly controlling the private data usage flow dynamically in the area of web services. Some reasoning can be made upon the observations to enhance the compliance of the privacy agreement and enrich the knowledge on misuses.