Data modeling in NoSQL databases is notoriously complex and driven by multiple and possibly conflicting requirements. Researchers have proposed methodologies to optimize schema design of a given domain for a given workload; however, due to the agile environment in which NoSQL databases are usually employed, both domain and workload are frequently subject to changes and evolution - possibly neutralizing the benefits of optimization. When this happens, the benefits of a new optimal schema design must be weighed against the costs of migrating the data. In this work, we empirically show the benefits of schema redesign in a real publicly available database. In particular, we identify multiple snapshots (in terms of domain extension and querying workload) in the 20+ years evolution of SkyServer, demonstrate how NoSQL schema optimization at a given time can later backfire, and evaluate the conditions under which data migration becomes beneficial. This takes us to define the foundations and challenges of a framework for continuous NoSQL database refactoring, with the goal of helping DBAs and data engineers decide if, when, and how a NoSQL database should be reconsidered to restore schema design optimality; special attention is paid to the optimization of data migration tasks scheduling.

Large Language Models (LLMs) can simulate human linguistic capabilities, thus producing a disruptive impact across several domains, including software engineering. In this paper we focus on a specific scenario of software engineering, that of conceptual design of multidimensional data cubes. The goal is to evaluate the performance of LLMs (precisely, of ChatGPT-4o) in multidimensional conceptual design using the Dimensional Fact Model as a reference. To this end, we formulate nine research questions to (i) understand the competences of ChatGPT in multidimensional conceptual design, following either a supply- or a demand-driven approach, and (ii) investigate to what extent they can be improved via prompt engineering. After describing the research process in terms of base criteria, technological setting, input/output format, prompt templates, test cases, and metrics for evaluating the results, we discuss the output of the experiment. Our main conclusions are that (i) when prompts are enhanced with detailed procedural instructions and examples, the results produced significantly improve in all cases; and (ii) overall, ChatGPT is better at demand-driven design than at supply-driven design.

OLAP streamlines the exploration of multidimensional data cubes by allowing decision-makers to build sessions of analytical queries via a ``point-and-click'' interaction. However, new scenarios are appearing in which alternative forms of user-system communication, based for instance on natural language, are necessary. To cope with these scenarios, we present VOOL, an extensible framework for the vocalization of the results of OLAP sessions. To avoid flooding the user with long and tedious descriptions, we choose to vocalize only selected insights automatically extracted from query results. Insights are quantitative and rich-in-semantics characterizations of the results of an OLAP query, and they also take into account the user's intentions as expressed by OLAP operators. Firstly, they are extracted using statistics and machine learning algorithms; then an optimization algorithm is applied to select the most relevant insights respecting a limit on the overall duration of vocalization. Finally, the selected insights are sorted into a comprehensive description that is vocalized to the user. After describing and formalizing our approach, we evaluate it from the points of view of efficiency, effectiveness, and operativity, also by comparing it with LLM-based applications.

Abstract Multi-model DBMSs, which support different data models with a fully integrated backend, have been shown to be beneficial to data warehouses and OLAP systems. Indeed, they can store data according to the multidimensional model and, at the same time, let each of its elements be represented through the most appropriate model. An open challenge in this context is the lack of methods for logical design. Indeed, in a multi-model context, several alternatives emerge for the logical representation of dimensions and facts. The goal of this paper is to devise a set of guidelines for the logical design of multi-model data warehouses so that the designer can achieve the best trade-off between features such as querying, storage, and ETL. To this end, for each model considered (relational, document-based, and graph-based) and for each type of multidimensional element (e.g., non-strict hierarchy) we propose some solutions and carry out a set of intra-model and inter-model comparisons. The resulting guidelines are then tested on a case study that shows all types of multidimensional elements.

The democratization of data access and the adoption of OLAP in scenarios requiring hand-free interfaces push towards the creation of smart OLAP interfaces. In this demonstration we present COOL, a tool supporting natural language COnversational OLap sessions. COOL interprets and translates a natural language dialogue into an OLAP session that starts with a GPSJ (Generalized Projection, Selection and Join) query. The interpretation relies on a formal grammar and a knowledge base storing metadata from a multidimensional cube. COOL is portable, robust, and requires minimal user intervention. It adopts an n-gram based model and a string similarity function to match known entities in the natural language description. In case of incomplete text description, COOL can obtain the correct query either through automatic inference or through interactions with the user to disambiguate the text. The goal of the demonstration is to let the audience evaluate the usability of COOL and its capabilities in assisting query formulation and ambiguity/error resolution.

Abstract The success of NoSQL DBMSs has pushed the adoption of polyglot storage systems that take advantage of the best characteristics of different technologies and data models. While operational applications take great benefit from this choice, analytical applications suffer the absence of schema consistency, not only between different DBMSs but within a single NoSQL system as well. In this context, the discipline of data science is steering analysts away from traditional data warehousing and toward a more flexible and lightweight approach to data analysis. The idea is to perform OLAP analyses in a pay-as-you-go manner across heterogeneous schemas and data models, where the integration is progressively carried out by the user as the available data is explored. In this paper, we propose an approach to support data analysis within a high-variety multistore, with heterogeneous schemas and overlapping records. Our approach supports relational, document, wide-column, and key-value data models by automatically handling both data model and schema heterogeneity through a dataspace layer on top of the underlying DBMSs. The expressiveness we enable corresponds to GPSJ queries, which are the most common class of queries in OLAP applications. We rely on nested relational algebra to define a cross-database execution plan. The system has been prototyped on Apache Spark.

We demonstrate SparkTune, a tool that supports the evaluation and tuning of Spark SQL workloads from multiple perspectives. Unlike Spark SQL's optimizer, which mainly relies on a rule-based model, SparkTune adopts a cost-based model for SQL queries; this enables the accurate estimation of execution times and the identification of cost and complexity factors in a user-defined workload. The estimate is based on the cluster configuration, the database statistics (both automatically retrieved by the tool) and the resources allocated to the workload. Thus, for any given cluster, database and workload, SparkTune is able to identify the best cluster configuration to run the workload, to estimate the price to run it on a cloud platform while evaluating the performance/price trade-off, and more. SparkTune turns the cluster tuning efforts from manual and qualitative to automatic, optimized and quantitative.

A key role in OLAP analyses of textual user-generated con-tent for social business intelligence (SBI) is played by topics, i.e., concepts of interest within a subject area. Topic hier-archies are irregular, heterogeneous, dynamic, and possibly schemaless; besides, unlike in traditional OLAP, di↵erent semantics for topic aggregation can be envisioned. In this demonstration we present an architecture for SBI based on meta-stars, a novel approach to topic modeling in ROLAP systems. By coupling meta-modeling with navigation tables, meta-stars can cope with changes in the schema of irregular hierarchies and with schemaless ones; besides, they enable a new class of OLAP queries based on semantically-aware aggregation. The demonstration will focus both on the hier-archy update process and on the querying expressiveness. 1.

Social business intelligence is the discipline of combining corporate data with user-generated content (UGC) to let decision-makers improve their business based on the trends perceived from the environment. A key role in the analysis of textual UGC is played by topics, meant as specific concepts of interest within a subject area. To enable aggregations of topics at different levels, a topic hierarchy is to be defined. Some attempts have been made to address some of the peculiarities of topic hierarchies, but no comprehensive solution has been found so far. The approach we propose to model topic hierarchies in ROLAP systems is called meta-stars. Its basic idea is to use meta-modeling coupled with navigation tables and with traditional dimension tables: navigation tables support hierarchy instances with different lengths and with non-leaf facts, and allow different roll-up semantics to be explicitly annotated; meta-modeling enables hierarchy heterogeneity and dynamics to be accommodated; dimension tables are easily integrated with standard business hierarchies. After outlining a reference architecture for social business intelligence and describing the meta-star approach, we discuss its effectiveness and efficiency by showing its querying expressiveness and by presenting some experimental results for query performances.