| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.77 MB | Adobe PDF |
Autores
Resumo(s)
This project examines the interplay between news avoidance, reader engagement, and content production within the Luxemburger Wort website. Drawing on data-driven strategies to comprehend reader preferences, the study investigates the impact of news avoidance and selection on media businesses. Leveraging text mining, Natural Language Processing (NLP), and statistical analyses, the research delves into the correlation between content production, consumption patterns, and reader engagement on Wort's website across three years.
The study's methodology integrates Text Mining (TM), NLP techniques, and topic modeling, employing TF-IDF and Latent Dirichlet Allocation (LDA) models. These methodologies enable the extraction of sentiments associated with news articles and categorization into topics, shedding light on reader preferences and content resonance. Word cloud analyses further elucidate the emotional character of news content.
The findings underscore the need for newsrooms to align content production with reader preferences across various sections and topics, emphasizing the significance of reader-centric approaches in optimizing news production efforts. The thesis concludes with a comprehensive review of literature, methodology, results, and implications for both academic theory and practical considerations within the media industry.
Descrição
Project Work presented as the partial requirement for obtaining a Master's degree in Data Driven Marketing, specialization in Digital Marketing and Analytics
Palavras-chave
News consumption News avoidance Audience analysis Text Minning Natural Language Processing Topic Modelling Topic Extraction SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure SDG 12 - Responsible production and consumption
