The rise of social media has transformed tourism research, providing new ways to understand travelers’ perspectives. Picture analysis, in particular, offers valuable insights into tourist preferences, popular attractions, and emotions conveyed through images. This analysis can be performed manually or with artificial intelligence. However, a significant challenge arises from the presence memes advertisements related informal markets, which complicate data usability. Manually filtering such...

This research's main objective is to analyse Online Travel Reviews (OTRs) related tourist attractions aiming at identifying recurring discussion topics/themes infer whether travellers make reference positive or negative experiences during their trips. study focuses on the case of Guanajuato, a Mexican cultural destination. It important mention that similar analyses have not been carried out any destination so far. OTRs are analysed using two Natural Language Processing approaches: Mutual...

Automatic discovery of underlying themes in a document collection is valuable task across many disciplines. Advanced techniques can be challenging for non-experts data science to understand. To address these challenges, this work proposes comprehensive deep-learning-based method gathering, preprocessing, analyzing, and classifying text discover topics extensive collections documents. This produces results understandable humans, which especially fields outside science. We tested the proposed...

Frequent similar pattern mining (FSP mining) allows for finding frequent patterns hidden from the classical approach. However, use of similarity functions implies more computational effort, necessitating development efficient algorithms FSP mining. This work aims to improve efficiency all FSPs when using Boolean and non-increasing monotonic functions. A data structure condense an object description collection, named FV-Tree , algorithm X-FSPMiner are proposed. The experimental results reveal...

Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of texts: semantically-informed similarity measure and edit distance. Both able to extract semantic information from either an external resource or distributed representation words, resulting in informative features training supervised classifier...

Author Profiling (AP) aims at predicting specific characteristics from a group of authors by analyzing their written documents. Many research has been focused on determining suitable features for modeling writing patterns authors. Reported results indicate that content-based continue to be the most relevant and discriminant solving this task. Thus, in paper, we present thorough analysis regarding appropriateness different distributional term representations (DTR) AP In regard, introduce...

This paper summarizes the thesis: "Author Profiling in Social Media with Multimodal Information." Our solution uses a multimodal approach to extracting information from written messages and images shared by users. Previous work has shown existence of useful for this task these modalities; however, our proposal goes further, demonstrating complementarity modalities when merging two sources information. To do this, we propose transform texts, them, have same framework representation both kinds...

This paper presents the framework and results from Rest-Mex track at IberLEF 2021. considered two tasks: Recommendation System Sentiment Analysis, using texts Mexican touristic places. The task consists in predicting degree of satisfaction that a tourist may have when recommending destination Nayarit, Mexico, based on places visited by tourists their opinions. On other hand, Analysis predicts polarity an opinion issued who traveled to most representative Guanajuato, Mexico. For both tasks,...

This study presents an analysis of the Rest-Mex forum task 2021, which is first international evaluation event using tourism-related (Online Travels Reviews - OTRs) data from Mexico. In that forum, 14 specialized sentiment systems were presented. The main contribution this research a method to successfully combine those on for OTRs. outputs used evaluate proposed combination schemes. trained and tested with 7,413 OTRs city Guanajuato, Mexico, well-known cultural destination. All them...

Purpose This study aims to present a framework for automatically collecting, cleaning and analyzing text (news articles, in this case) provide valuable decision-making information destination management organizations. Keeping record of certain aspects the projected image an attraction (Cancun study) will grant design better strategies promotion administration destinations without time-consuming effort manually evaluating high quantities textual information. Design/methodology/approach Using...

Currently, customer service continues to grow because many public and private companies offer a vast number of services. Chatbots significantly improve service, in that they allow direct relationship with the consumer at any time provide marketing groups valuable data about their preferences. These characteristics make chatbots an exciting instrument for organizations; addition, users remain satisfied service. This work aims design, develop, evaluate chatbot system provides interactive means...

Efficient energy management is critical to building inclusive, safe, resilient, and sustainable cities human settlements. Optimizing the operation planning of smart grids crucial in this regard remains an active research area. The "Competition on Evolutionary Computation Energy Domain" has been held annually since 2017. Its 2023 edition focuses two problems: Risk-based optimization resource considering uncertainty high penetration distributed resources, Long-term transmission network...

Promoting a destination is major task for Destination Marketing Organizations (DMOs). Although DMOs control, to some extent, the information presented travelers (controlled sources), there are other different sources of (uncontrolled sources) that could project an unfavorable image destination. Measuring differences between would help design strategies mitigate negative factors. In this way, we propose deep learning-based approach automatically measure changes images from controlled and...

The goal of Author Profiling (AP) is to identify demographic aspects (e.g., age, gender) from a given set authors by analyzing their written texts. Recently, the AP task has gained interest in many problems related computer forensics, psychology, marketing, but specially those with social media exploitation. As known, data shared through wide range modalities text, images and audio), representing valuable information be exploited for extracting insights users. Nevertheless, most current work...