English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The rising influence of social media platforms in various domains, includingtourism, has highlighted the growing need for efficient and automated naturallanguage processing (NLP) approaches to take advantage of this valuableresource. However, the transformation of multilingual, unstructured, andinformal texts into structured knowledge often poses significant challenges.  In this work, we evaluate and compare few-shot, pattern-exploiting andfine-tuning machine learning techniques on large multilingual language models(LLMs) to establish the best strategy to address the lack of annotated data for3 common NLP tasks in the tourism domain: (1) Sentiment Analysis, (2) NamedEntity Recognition, and (3) Fine-grained Thematic Concept Extraction (linked toa semantic resource). Furthermore, we aim to ascertain the quantity ofannotated examples required to achieve good performance in those 3 tasks,addressing a common challenge encountered by NLP researchers in theconstruction of domain-specific datasets.  Extensive experimentation on a newly collected and annotated multilingual(French, English, and Spanish) dataset composed of tourism-related tweets showsthat current few-shot learning techniques allow us to obtain competitiveresults for all three tasks with very little annotation data: 5 tweets perlabel (15 in total) for Sentiment Analysis, 10% of the tweets for locationdetection (around 160) and 13% (200 approx.) of the tweets annotated withthematic concepts, a highly fine-grained sequence labeling task based on aninventory of 315 classes.  This comparative analysis, grounded in a novel dataset, paves the way forapplying NLP to new domain-specific applications, reducing the need for manualannotations and circumventing the complexities of rule-based, ad hoc solutions.

Optimal Strategies to Perform Multilingual Analysis of Social Content for a Novel Dataset in the Tourism Domain