A Comparative Assessment of State-Of-The-Art Methods for Multilingual Unsupervised Keyphrase Extraction

Giarelis, Nikolaos; Kanakaris, Nikos; Karacapilidis, Nikos

doi:10.1007/978-3-030-79150-6_50

Cited by 19 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To understand the impact of this kind of network on group behavior and individual influence, SNA can be used to describe its structure (Wasserman and Faust 1994 ). Studies on web discourse primarily focus on computational aspects (Herring 2013 ), such as NLP (Yuksel and Tan 2018 ; Giarelis et al 2021 ), online content analysis, and speech analysis (Moser et al 2013 ; Kok and Rogers 2017 ; Pennington 2017 ; Goritz et al 2019 ), with a significant emphasis on text analysis and utilizing other knowledge areas. However, SNA and semantic analysis of posts have not received much attention and remain largely theoretical (Zhao et al 2021 ).…”

Section: Social Network Analysis and Decision-making Support For Airl...mentioning

confidence: 99%

Enhancing decision-making support by mining social media data with social network analysis

Freire

Antunes

Costa

2023

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

This paper explores the use of social network analysis (SNA) on airlines’ online social networks (OSNs) to extract valuable information for decision support, by analyzing interactions and discursive exchanges between users. The research is focused on fostering customer service of an airline company during a strike period, namely by detecting influential customers (whether satisfied or dissatisfied), address pending requests, and enhancing customer satisfaction, thus promoting issue-solving, and increasing responsiveness. The methodology involves analyzing data from the Facebook account of an airline company, using SNA to structure the data, and calculating metrics to detect possible situations to be addressed by customer service. The research concludes that it is possible to extract valuable information for decision support by analyzing the metrics that were built over the interactions and discursive exchanges between OSN users. SNA metrics enable to measure airline’s call-center performance in terms of speed of answer and customer satisfaction, to identify active users requiring additional support, as well as highly influential customers who may impact on the overall customer satisfaction, thus helping to resolve issues more efficiently. This study provides both theoretical and practical implications: it contributes to the existing literature by integrating social interaction and SNA for decision support in airline’s service context; and it provides practical insights into how companies can use SNA metrics to improve customer service. The research also highlights and corroborates the importance of monitoring social media interactions for decision-making and improving customer service.

show abstract

Section: Social Network Analysis and Decision-making Support For Airl...mentioning

confidence: 99%

Enhancing decision-making support by mining social media data with social network analysis

Freire

Antunes

Costa

2023

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…This paper focuses mostly on showcasing the applications of the T5 generative language model [13] and comparing its performance to text classification (extremeText / fastText) [17] [10] and statistical terminology extraction (C / NC-values) [7] as baseline methods. Although the complementarity of statistical and transformer-based approaches to keyword extraction has been explored before [8], we are not aware of any published assessment of text-to-text generative models on this task.…”

Section: Keyword Extraction and Generationmentioning

confidence: 99%

“…Logistyka (logistics) is the only potentially irrelevant keyword in this subset which may have resulted from some over-fitting of the model on the original domain of scientific abstracts. (4) seal break (4) plomba na liczniku (8) seal on meter (8) PESEL (2) National Identification Number (2) weryfikacja tożsamości (1) identity verification (1)…”

Section: Customer Support Dialoguesmentioning

confidence: 99%

Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer

Pęzik¹,

Mikołajczyk-Bareła²,

Wawrzyński³

et al. 2022

Preprint

View full text Add to dashboard Cite

The paper explores the relevance of the Text-To-Text Transfer Transformer language model (T5) for Polish (plT5) to the task of intrinsic and extrinsic keyword extraction from short text passages. The evaluation is carried out on the new Polish Open Science Metadata Corpus (POSMAC), which is released with this paper: a collection of 216,214 abstracts of scientific publications compiled in the CURLICAT project. We compare the results obtained by four different methods, i.e. plT5kw, extremeText, TermoPL, KeyBERT and conclude that the plT5kw model yields particularly promising results for both frequent and sparsely represented keywords. Furthermore, a plT5kw keyword generation model trained on the POSMAC also seems to produce highly useful results in cross-domain text labelling scenarios. We discuss the performance of the model on news stories and phone-based dialog transcripts which represent text genres and domains extrinsic to the dataset of scientific abstracts. Finally, we also attempt to characterize the challenges of evaluating a text-to-text model on both intrinsic and extrinsic keyword extraction.

show abstract

“…By acquiring ranked words, it accurately extracts just noun phrases from datasets, not keyphrases. In ranking phase, unimportant keywords are used, although this does not always screen out small scoring terms, providing longer keywords greater scores [22].…”

Section: Unsupervised Techniquesmentioning

confidence: 99%

“…Again, because of the huge number of complex processes, statistical unsupervised techniques such as [15,21] are computationally expensive. Graph-based unsupervised approaches perform badly because of their inability to detect cohesion amongst numerous words that compose a keyphrase [22][23][24][25][26][27]. Finally, TeKET [14] is extremely versatile and acts similarly to TF-IDF for short data lengths.…”

Section: Introductionmentioning

confidence: 99%

A New Unsupervised Technique to Analyze the Centroid and Frequency of Keyphrases from Academic Articles

et al. 2022

View full text Add to dashboard Cite

Automated keyphrase extraction is crucial for extracting and summarizing relevant information from a variety of publications in multiple domains. However, the extraction of good-quality keyphrases and the summarising of information to a good standard have become extremely challenging in recent research because of the advancement of technology and the exponential development of digital sources and textual information. Because of this, the usage of keyphrase features for keyphrase extraction techniques has recently gained tremendous popularity. This paper proposed a new unsupervised region-based keyphrase centroid and frequency analysis technique, named the KCFA technique, for keyphrase extraction as a feature. Data/datasets collection, data pre-processing, statistical methodologies, curve plotting analysis, and curve fitting technique are the five main processes in the proposed technique. To begin, the technique collects multiple datasets from diverse sources, which are then input into the data pre-processing step by utilizing some text pre-processing processes. Afterward, the region-based statistical methodologies receive the pre-processed data, followed by the curve plotting examination and, lastly, the curve fitting technique. The proposed technique is then tested and evaluated using ten (10) best-accessible benchmark datasets from various disciplines. The proposed approach is then compared to our available methods to demonstrate its efficacy, advantages, and importance. Lastly, the results of the experiment show that the proposed method works well to analyze the centroid and frequency of keyphrases from academic articles. It provides a centroid of 706.66 and a frequency of 38.95% in the first region, 2454.21 and 7.98% in the second region, for a total frequency of 68.11%.

show abstract

A Comparative Assessment of State-Of-The-Art Methods for Multilingual Unsupervised Keyphrase Extraction

Cited by 19 publications

References 16 publications

Enhancing decision-making support by mining social media data with social network analysis

Enhancing decision-making support by mining social media data with social network analysis

Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer

A New Unsupervised Technique to Analyze the Centroid and Frequency of Keyphrases from Academic Articles

Contact Info

Product

Resources

About