This study aims to provide insights into the COVID-19-related communication on Twitter in the Republic of Croatia. For that purpose, we developed an NL-based framework that enables automatic analysis of a large dataset of tweets in the Croatian language. We collected and analysed 206,196 tweets related to COVID-19 and constructed a dataset of 10,000 tweets which we manually annotated with a sentiment label. We trained the Cro-CoV-cseBERT language model for the representation and clustering of tweets. Additionally, we compared the performance of four machine learning algorithms on the task of sentiment classification. After identifying the best performing setup of NLP methods, we applied the proposed framework in the task of characterisation of COVID-19 tweets in Croatia. More precisely, we performed sentiment analysis and tracked the sentiment over time. Furthermore, we detected how tweets are grouped into clusters with similar themes across three pandemic waves. Additionally, we characterised the tweets by analysing the distribution of sentiment polarity (in each thematic cluster and over time) and the number of retweets (in each thematic cluster and sentiment class). These results could be useful for additional research and interpretation in the domains of sociology, psychology or other sciences, as well as for the authorities, who could use them to address crisis communication problems.

In natural language processing, text needs to be transformed into a machine-readable representation before any processing. The quality of further natural language processing tasks greatly depends on the quality of those representations. In this survey, we systematize and analyze 50 neural models from the last decade. The models described are grouped by the architecture of neural networks as shallow, recurrent, recursive, convolutional, and attention models. Furthermore, we categorize these models by representation level, input level, model type, and model supervision. We focus on task-independent representation models, discuss their advantages and drawbacks, and subsequently identify the promising directions for future neural text representation models. We describe the evaluation datasets and tasks used in the papers that introduced the models and compare the models based on relevant evaluations. The quality of a representation model can be evaluated as its capability to generalize to multiple unrelated tasks. Benchmark standardization is visible amongst recent models and the number of different tasks models are evaluated on is increasing.

Node centrality is one of the most frequently revisited network theoretical concepts, which got many calculation method alternatives, each of them being conceived on different empirical or theoretical network abstractions. The vast majority of centrality measures produced up to date were conceived on static network abstractions (the so-called "snapshot" networks), which arguably are less realistic than dynamic (temporal) network abstractions. The new, temporal node centrality measure that we offer with this article, is based on an uncommon abstraction, of a space-time network derived from service schedules (timetables). The proposed measure was designed to rank nodes of a space-time network based on their spread or transmission potential, and was subsequently implemented on the network of sea ferry transportation derived from the aggregated schedules for sea ferry liner shipping services in Europe, as they occurred in the month of August, 2015. The main feature of our measure, named "the Spread Potential", is the evaluation of the potential of a node in the network for transmitting disease, information (e.g. rumours or false news), as well as other phenomena, whichever support a space-time network abstraction from regular and scheduled services with some known carrying capacities. Such abstractions are, for instance, of the transportation networks (e.g. of airline or maritime shipping or the wider logistics (delivery) networks), networks of medical (hospital) services, educational (teaching) services, and virtually, of any other scheduled networked phenomenon. The article also offers the perspectives of the measure's applicability on the non-scheduled space-time network abstractions.

Measuring the semantic similarity of texts has a vital role in various tasks from the field of natural language processing. In this paper, we describe a set of experiments we carried out to evaluate and compare the performance of different approaches for measuring the semantic similarity of short texts. We perform a comparison of four models based on word embeddings: two variants of Word2Vec (one based on Word2Vec trained on a specific dataset and the second extending it with embeddings of word senses), FastText, and TF-IDF. Since these models provide word vectors, we experiment with various methods that calculate the semantic similarity of short texts based on word vectors. More precisely, for each of these models, we test five methods for aggregating word embeddings into text embedding. We introduced three methods by making variations of two commonly used similarity measures. One method is an extension of the cosine similarity based on centroids, and the other two methods are variations of the Okapi BM25 function. We evaluate all approaches on the two publicly available datasets: SICK and Lee in terms of the Pearson and Spearman correlation. The results indicate that extended methods perform better from the original in most of the cases.

No abstract