Automatska ekstrakcija ključnih riječi iz teksta aktualan je istraživački problem u području računalne analize prirodnog jezika i pretraživanja informacija. Iako su razvijene brojne metode za ...ekstrakciju ključnih riječi iz teksta, njihova učinkovitost ovisna je o brojnim faktorima poput pristupa kojim su konstruirane, domene na koju su prilagođene, vrste jezika ili zadataka za koji su konstruirane i sl., a samim time prostor za napredak u smislu nadogradnje i poboljšanja, uvijek postoji. U ovom radu objašnjene su i rekonstruirane dvije postojeće metode – RAKE i MAUI, a koje su standardni predstavnici nenadzirane i nadzirane skupine metoda. Eksperimentalno je ispitano mogu li metode uspješno ekstrahirati ključne riječi iz tekstova pisanih na talijanskom jeziku, na kojem do sada nisu usporedno testirane. Za potrebe eksperimenta prikupljeni su i ručno označeni talijanski tekstovi. Efikasnost MAUI metode pokazala se perspektivnijom u odnosu na RAKE metodu što je već ranije potvrđeno u eksperimentu ekstrakcije ključnih riječi iz tekstova pisanih na engleskom jeziku.
The paper surveys methods and approaches for the task of keyword extraction. The systematic review of methods was gathered which resulted in a comprehensive review of existing approaches. Work ...related to keyword extraction is elaborated for supervised and unsupervised methods, with a special emphasis on graph-based methods. Various graph-based methods are analyzed and compared. The paper provides guidelines for future research plans and encourages the development of new graph-based approaches for keyword extraction.
Retweet prediction is an important task in the context of various problems, such as information spreading analysis, automatic fake news detection, social media monitoring, etc. In this study, we ...explore retweet prediction based on heterogeneous data sources. In order to classify a tweet according to the number of retweets, we combine features extracted from the multilayer network and text. More specifically, we introduce a multilayer framework for the multilayer network representation of Twitter. This formalism captures different users’ actions and complex relationships, as well as other key properties of communication on Twitter. Next, we select a set of local network measures from each layer and construct a set of multilayer network features. We also adopt a BERT-based language model, namely Cro-CoV-cseBERT, to capture the high-level semantics and structure of tweets as a set of text features. We then trained six machine learning (ML) algorithms: random forest, multilayer perceptron, light gradient boosting machine, category-embedding model, neural oblivious decision ensembles, and an attentive interpretable tabular learning model for the retweet-prediction task. We compared the performance of all six algorithms in three different setups: with text features only, with multilayer network features only, and with both feature sets. We evaluated all the setups in terms of standard evaluation measures. For this task, we first prepared an empirical dataset of 199,431 tweets in Croatian posted between 1 January 2020 and 31 May 2021. Our results indicate that the prediction model performs better by integrating multilayer network features with text features than by using only one set of features.
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.
Online media play an important role in public health emergencies and serve as essential communication platforms. Infoveillance of online media during the COVID-19 pandemic is an important step toward ...gaining a better understanding of crisis communication.
The goal of this study was to perform a longitudinal analysis of the COVID-19-related content on online media based on natural language processing.
We collected a data set of news articles published by Croatian online media during the first 13 months of the pandemic. First, we tested the correlations between the number of articles and the number of new daily COVID-19 cases. Second, we analyzed the content by extracting the most frequent terms and applied the Jaccard similarity coefficient. Third, we compared the occurrence of the pandemic-related terms during the two waves of the pandemic. Finally, we applied named entity recognition to extract the most frequent entities and tracked the dynamics of changes during the observation period.
The results showed no significant correlation between the number of articles and the number of new daily COVID-19 cases. Furthermore, there were high overlaps in the terminology used in all articles published during the pandemic with a slight shift in the pandemic-related terms between the first and the second waves. Finally, the findings indicate that the most influential entities have lower overlaps for the identified people and higher overlaps for locations and institutions.
Our study shows that online media have a prompt response to the pandemic with a large number of COVID-19-related articles. There was a high overlap in the frequently used terms across the first 13 months, which may indicate the narrow focus of reporting in certain periods. However, the pandemic-related terminology is well-covered.
Automatic keyword extraction takes a great interest as a research issue in the field of natural language processing and information retrieval. Although numerous methods for keyword extraction task ...have been developed, their effectiveness depends on many factors such as the approach used in method development, the domain to which they are adapted, the type of language or tasks for which they are constructed, etc., and still, there is a room for progress and improvements. In this paper, two existing methods are explained and reconstructed - RAKE and MAUI, which are the standard representatives of the unsupervised and supervised group of keyword extraction methods. It was experimentally tested whether the methods could successfully extract keywords from texts written in Italian, which had not been tested so far. For the experimental purposes, Italian texts were collected and annotated with keywords. The effectiveness of the MAUI method proved to be more promising than the RAKE method, which was confirmed earlier in the keyword extraction experiment from texts written in English.
The polarity of online news publications thematically related to COVID-19 is analysed. A collection of sentiment annotations for news articles written in the Croatian language was created and compose ...a new Cro-CoV-Senti-articles-2020 dataset. The news article's sentiment is derived from the reactions of portal readers. In addition, well-known sentiment analysis approaches that use lexicons and machine learning algorithms have been implemented to automatically determine the sentiment of online news. Besides, the VADER framework was used in parallel. It has been found that for the purposes of crisis communication analysis when rapid analysis solutions are needed, existing tools can be used for preliminary sentiment analysis despite some technical shortcomings. However, for a more extensive analysis of the media space and highly valuable insights, some refinements are needed. This preliminary analysis, on a sample of approximately 3,400 newspaper articles related to COVID-19, finds that readers perceive as many as two-thirds of articles negatively rather than positively.
In this study, a computational content analysis of crisis-related articles published in electronic media for two crises, namely COVID-19 and the Russia-Ukraine war, is conducted. A set of methods for ...content analysis is proposed, which involves the combination of exploratory analysis, main topic filtering, and performing named entity recognition enhanced with network analysis. The main finding of this study is a list of the most frequently mentioned persons, locations, and organizations in the news articles of both crises and how they are connected. The results obtained affirm the suitability of the proposed approach for crisis-related content analysis.
Selectivity-Based Keyword Extraction Method Beliga, Slobodan; Meštrović, Ana; Martinčić-Ipšić, Sanda
International journal on semantic web and information systems,
07/2016, Volume:
12, Issue:
3
Journal Article
Peer reviewed
In this work the authors propose a novel Selectivity-Based Keyword Extraction (SBKE) method, which extracts keywords from the source text represented as a network. The node selectivity value is ...calculated from a weighted network as the average weight distributed on the links of a single node and is used in the procedure of keyword candidate ranking and extraction. The authors show that selectivity-based keyword extraction slightly outperforms an extraction based on the standard centrality measures: in/out-degree, betweenness and closeness. Therefore, they include selectivity and its modification – generalized selectivity as node centrality measures in the SBKE method. Selectivity-based extraction does not require linguistic knowledge as it is derived purely from statistical and structural information of the network. The experimental results point out that selectivity-based keyword extraction has a great potential for the collection-oriented keyword extraction task.
Croatian is poorly resourced and highly inflected language from Slavic language family. Nowadays, research is focusing mostly on English. We created a new word analogy corpus based on the original ...English Word2vec word analogy corpus and added some of the specific linguistic aspects from Croatian language. Next, we created Croatian WordSim353 and RG65 corpora for a basic evaluation of word similarities. We compared created corpora on two popular word representation models, based on Word2Vec tool and fastText tool. Models has been trained on 1.37B tokens training data corpus and tested on a new robust Croatian word analogy corpus. Results show that models are able to create meaningful word representation. This research has shown that free word order and the higher morphological complexity of Croatian language influences the quality of resulting word embeddings.