Abstract

Abstract
Time expressions embedded in text are important for many downstream tasks in NLP and IR. They have been, for example, utilized for timeline summarization, named entity recognition, temporal information retrieval, question answering and others. In this paper, we introduce a novel analytical approach to analyzing characteristics of time expressions in diachronic text collections. Based on a collection of news articles published over a 33-years' long time span, we investigate several aspects of time expressions with a focus on their interplay with publication dates of containing documents. We utilize a graph-based representation of temporal expressions to represent them through their co-occurring named entities. The proposed approach results in several observations that could be utilized in automatic systems that rely on processing temporal signals embedded in text. It could be also of importance for professionals (e.g., historians) who wish to understand fluctuations in collective memories and collective expectations based on large-scale, diachronic document collections. © 2022 ACM.

Abstract
In this paper, we consider a permutation flowshop problem, with a weighted squared tardiness objective function, which addresses an important criterion for many customers. Our objective is to find metaheuristics that can, within acceptable computational times, provide sizeable improvements in solution quality over the best existing procedure (a dispatching rule followed by an improvement method). We consider four metaheuristics, namely iterated local search (ILS), iterated greedy (IG), variable greedy (VG) and steady-state genetic algorithms (SSGA). These are known for performing well on permutation flowshops and/or on tardiness criteria. For each metaheuristic, four versions are developed, differing on the choice of initial sequence and/or local search. Additionally, four different time limits are considered. Therefore, a total of 64 sets of results are obtained. The results show that all procedures greatly outperform the best existing method. The IG procedures provide the best results, followed by the SSGA procedures. The VG methods are usually inferior to SSGA, while the ILS metaheuristics tend to be the worst performers. The four metaheuristics prove to be robust in what regards initial solution and local search method, since both have little effect on the performance of the metaheuristics. Increasing the time limit does improve the performance of all procedures. Still, a sizeable improvement is obtained even for the lowest time limit. Therefore, even under restrictive time limits, the metaheuristics greatly outperform the best existing procedure.

Abstract
Scheduling jobs in a no-wait flow shop with the objective of minimising total earliness and tardiness is the problem addressed in this paper. Idle time may be needed on the first machine due to the no-wait restriction. A model is developed that shows additional idle can be inserted on the first machine to help reduce earliness. Several dispatching heuristics previously used in other environments were modified and tested. A two-phased procedure was also developed, estimating additional idle in the first phase, and applying dispatching heuristics in the second phase. Several versions of an insertion improvement procedure were also developed. The procedures are tested on instances of various sizes and due date tightness and range. The results show the two-phase heuristics are more effective than the simple rules, and the insertion search improvement procedure can provide considerable improvements.

Abstract
In an earlier work we described and applied a methodology to find an adequate distribution for Nearly Gaussian (NG) random variables. In this work, we compare two different methods, m1 and m2 to estimate a power transform parameter for NG random variables. The m1 method is heuristic and based on sample kurtosis. Herein, we describe and apply it using a new reduced data set. The second method m2 is based on the maximization of a pseudo-log-likelihood function. As an application, we compare the performance of each method using high power statistical tests for the null hypothesis of normality. The data we use are the daily errors in the forecasts of maximum and minimum temperatures in the city of Porto. We show that the high kurtosis of the original data is due to high correlation among data. We also found that although consistent with normality the data is better fitted by distributions of the power normal (PN) family than by the normal distribution. Regarding the comparison of the two parameter estimation methods we found that the m1 provides higher p-values for the observed statistics tests except for the Shapiro-Wilk test.

Abstract
Explainable recommendations enable users to understand why certain items are suggested and, ultimately, nurture system transparency, trustworthiness, and confidence. Large crowdsourcing recommendation systems ought to crucially promote authenticity and transparency of recommendations. To address such challenge, this paper proposes the use of stream-based explainable recommendations via blockchain profiling. Our contribution relies on chained historical data to improve the quality and transparency of online collaborative recommendation filters - Memory-based and Model-based - using, as use cases, data streamed from two large tourism crowdsourcing platforms, namely Expedia and TripAdvisor. Building historical trust-based models of raters, our method is implemented as an external module and integrated with the collaborative filter through a post-recommendation component. The inter-user trust profiling history, traceability and authenticity are ensured by blockchain, since these profiles are stored as a smart contract in a private Ethereum network. Our empirical evaluation with HotelExpedia and Tripadvisor has consistently shown the positive impact of blockchain-based profiling on the quality (measured as recall) and transparency (determined via explanations) of recommendations.