We analyze the information credibility of news propagated through Twitter, a popular microblogging service. Previous research has shown that most messages posted on Twitter are truthful, but service is also used to spread misinformation and false rumors, often unintentionally.

In this article we explore the behavior of Twitter users under an emergency situation. particular, analyze activity related to 2010 earthquake in Chile and characterize hours days following disaster. Furthermore, perform a preliminary study certain social phenomenons, such as dissemination false rumors confirmed news. We how information propagated through network, with purpose assessing reliability source extreme circumstances. Our analysis shows that propagation tweets correspond differs...

Abstract Purpose Twitter is a popular microblogging service which has proven, in recent years, its potential for propagating news and information about developing events. The purpose of this paper to focus on the analysis credibility Twitter. our research establish if an automatic discovery process relevant credible events can be achieved. Design/methodology/approach follows supervised learning approach task classification A first classifier decides cascade corresponds newsworthy event. Then...

Twitter sentiment analysis or the task of automatically retrieving opinions from tweets has received an increasing interest web mining community. This is due to its importance in a wide range fields such as business and politics. People express sentiments about specific topics entities with different strengths intensities, where these are strongly related their personal feelings emotions. A number methods lexical resources have been proposed analyze natural language texts, addressing opinion...

Social media services have spread throughout the world in just a few years. They become not only new source of information, but also mechanisms for societies world-wide to organize themselves and communicate. Therefore, social has very strong impact many aspects -- at personal level, business, politics, among others. In spite its fast adoption, little is known about usage different countries, whether patterns behavior remain same or not. To provide deep understanding differences between...

The package diverse provides an easy-to-use interface to calculate and visualize different aspects of diversity in complex systems.In recent years, increasing number research projects social interdisciplinary sciences, including fields like innovation studies, scientometrics, economics, network science have emphasized the role diversification sophistication socioeconomic systems.However, so far no dedicated exists that covers needs these emerging teams.Most packages about tend be created...

Software assistants have significantly impacted software development for both practitioners and students, particularly in capstone projects. The effectiveness of these tools varies based on their knowledge sources; with localized, domain-specific may limitations, while like ChatGPT, using broad datasets, might offer recommendations that do not always match the specific objectives a course. Addressing gap current educational technology, this paper introduces an AI Knowledge Assistant...

Web usage mining is a main research area in focused on learning about users and their interactions with sites. Main challenges are the application of data techniques to an efficient way discovery non trivial user behaviour patterns. In this paper we focus attention search engines analyzing query log showing several models how use engine results.

The Modified Mercalli intensity scale (Mercalli for short) is a qualitative measure used to express the perceived of an earthquake in terms damages. Accurate reports are vital estimate type emergency response required particular earthquake. In addition, needed possible consequences strong earthquakes future, based on effects previous events. Emergency offices and seismological agencies worldwide charge producing each affected location after However, this task relies heavily human observers...

Abstract The rise of bots that mimic human behavior represents one the most pressing threats to healthy information environments on social media. Many are designed increase visibility low-quality content, spread misinformation, and artificially boost reach brands politicians. These can also disrupt civic action coordination, such as by flooding a hashtag with spam undermining political mobilization. Social media platforms have recognized these malicious bots’ risks implemented strict...

The rise of bots and their influence on social networks is a hot topic that has aroused the interest many researchers. Despite efforts to detect bots, it still difficult distinguish them from legitimate users. Here, we propose simple yet effective semi-supervised method allows distinguishing between users with high accuracy. learns joint representation connections interactions by leveraging graph-based learning. Then, proximity graph derived user embeddings, sample used as seeds for label...

The variety of goods obtained from root crops, particularly cassava and sweet potatoes, is getting low, thereby affecting their sustainability. researcher has produced a syrup by combining potato starch. This study evaluated the sensory acceptability, proximate characteristics, production cost blend with amylase. procedure involves boiling starch purified water for 30 minutes; thereafter, amylase enzyme incorporated into slurry. stirred combined slurry, converting it liquid, then simmered...

This study analyzes the discourse of reporters, editors and audiences in focus groups in-depth interviews, examining expectations on journalists when facing misinformation. While both agree that journalistic information is critical, how this expectation met varies. On one hand, audience's way knowing involves diverse assessments regarding valuable information; also, they are dubious about journalists' intentions. other exhibit a limited understanding informational needs encounter practical...

Abstract Background Large language models (LLMs) like GPT-4o have shown promise in advancing medical decision-making and education. However, their performance Spanish-language contexts remains underexplored. This study evaluates the effectiveness of single-agent multi-agent strategies answering questions from EUNACOM, a standardized licensure exam Chile, across 21 specialties. Methods was tested on 1,062 multiple-choice publicly available EUNACOM preparation materials. Single-agent included...