The fourth agricultural revolution has popularized the usage of information and communication technologies (ICTs) in farms, which has been shown to improve productivity [1], reduce labor, and help mitigate unforeseen circumstances through predictive modeling [2]. This practice is referred to as smart farming and has seen several successful applications worldwide in recent years [3]. Smart farming projects are conducted over a long period of time and can have a noteworthy impact [4], [5], [6], [7], [8]. Some major concerns regarding the new smart farming technologies are data and privacy concerns [9], lack of reliable infrastructure and equipment [10], laws and regulations in a particular location, training, and skill acquisition [11], and apprehension associated with the adoption of new technology. Farmers need to be provided with proper training and support to help them adopt new sustainable practices [12], [13]. It is also important to monitor the sentiments of farmers and the public toward innovations in the field of smart farming to allow for easier adaptation to changes and enhance future projects. Sentiment analysis can highlight the aspects of smart farming, which are positively and negatively perceived by the public, which can uncover areas for improvement. Insights derived through sentiment analysis can be invaluable for various shareholders, as it can signal market demand for smart farming tools.

Many businesses are heavily reliant on data and many people working in business like to have almost constant access to this data. Mobile phones provide users with access to a wide range of office applications, including word processors, email applications, and spreadsheet applications. However the limitations of the mobile devices can cause a number of usability issues which may limit the productivity of users of these devices. This paper presents the authors’ investigation of the usability of mobile spreadsheet applications. Through a controlled study they examined the performance of users using a mobile spreadsheet application to perform a series of simple tasks, such as finding data and altering values in the spreadsheet. The authors found that although mobile spreadsheet applications can be effective, they are highly inefficient due to a large number of usability issues.

The advent of Large Language Models (LLMs) has advanced the benchmark in various Natural Language Processing (NLP) tasks. However, large amounts of labelled training data are required to train LLMs. Furthermore, data annotation and training are computationally expensive and time-consuming. Zero and few-shot learning have recently emerged as viable options for labelling data using large pre-trained models. Hate speech detection in mix-code low-resource languages is an active problem area where the use of LLMs has proven beneficial. In this study, we have compiled a dataset of 100 YouTube comments, and weakly labelled them for coarse and fine-grained misogyny classification in mix-code Hinglish. Weak annotation was applied due to the labor-intensive annotation process. Zero-shot learning, one-shot learning, and few-shot learning and prompting approaches have then been applied to assign labels to the comments and compare them to human-assigned labels. Out of all the approaches, zero-shot classification using the Bidirectional Auto-Regressive Transformers (BART) large model and few-shot prompting using Generative Pre-trained Transformer- 3 (ChatGPT-3) achieve the best results

Although artificial intelligence (AI) models have demonstrated great success and efficiency in automatically countering online hate speech and misogyny, they suffer from a lack of explainability and transparency. Explainable artificial intelligence (XAI) is an apparent solution to make opaque black‐box models more explainable, but remains under‐explored for low resource and code‐mixed languages. In this study, user‐based evaluation of 3 explainability techniques for a misogyny classifier has been performed through simulatability, what‐if explainability, and a qualitative feedback that covers several key dimensions. The participants were also required to mark the rationales to justify their predictions, and required to answer an open‐ended question regarding their opinion on the explanations. Analysis of the results from 10 participants highlights that Integrated Gradients (IG) was more consistent and plausible than other techniques, and their preference for token attribution heatmaps and bar plots over natural language explanations (NLE).

Background: This study aimed to examine the dose-response relationship between training load and aspects of physical fitness in English Premier League (EPL) U23 soccer players. Materials and Methods: Seven male EPL U23 outfield soccer players (age 20.1±1.1 years) participated in this study and performed the Bronco test on five occasions within one season. Individualised running thresholds were employed using maximal aerobic speed (MAS), anaerobic speed reserve (ASR) and maximal sprint speed (MSS) values utilising a GPS system. Results: No significant differences in the Bronco performance between the tests (p > 0.05, ES = 0.101) were observed. Distance covered above 30% ASR (r = -0.51) and time spent above 30% ASR (r = -0.54) over a 2-week period displayed a moderate negative linear relationship with Bronco performance. Conclusions: ASR-based training load variables displayed the highest correlations with Bronco results. These findings support practitioners to individualise high-speed running thresholds.