Sökning: "text clustering"
Visar resultat 1 - 5 av 63 uppsatser innehållade orden text clustering.
1. The Sound of Skepticism Analyzing Climate Change Denial in Swedish Podcasts and YouTube Channels
Kandidat-uppsats, Göteborgs universitet / / Institutionen för sociologi och arbetsvetenskapSammanfattning : This study explores Sweden's climate change denial by analyzing the spoken-word discourse of its countermovement, focusing on digital media content from Swedish parliament member Elsa Widding with an aim to provide empirical insights into the discourse of Sweden's Climate Change Countermovement (CCCM). Questions guiding this study are: What are the most prevalent topics and themes related to climate change denial and skepticism? How do they align with established categories of climate change denial, shaping the overall narrative? What mobilizing ideas and meanings are present, how are they shaped, and how do they contribute to the movement's goals? The material consists of Elsa Widding's complete audio-based "movement texts'' from 2019-2023, including YouTube content, podcasts, and appearances on Riks, totaling over 2000 minutes of audio transcribed into text via AI technology. LÄS MER
2. Fixation and Machine Learning A new method for measuring fixation in internet users using machine learning and natural language processing
Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Fixation — the state of mind where an individual is intensely fixated on one individual, activity or idea — can be an early warning sign of an individual that will later go on to commit violent acts. This paper details the development of a method that measures fixation from texts written on internet forums, a method that could (when expanded) be a part of threat assessment and prevention of violence. LÄS MER
3. Domain Knowledge and Representation Learning for Centroid Initialization in Text Clustering with k-Means : An exploratory study
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Text clustering is a problem where texts are partitioned into homogeneous clusters, such as partitioning them based on their sentiment value. Two techniques to address the problem are representation learning, in particular language representation models, and clustering algorithms. LÄS MER
4. IMPROVING NONDISCRIMINATIVE CLASSIFIERS WITH THE HELP OF CLUSTERING : Enhancing Text Classification: Using Clustering For Improved Classifier Performance
Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : A common classification task of today is classifying resources that consist of words. Nondiscriminative classifiers are a popular type of classifiers for such classification. This paper presents a study that determines whether a method of using clusters of words found in training data can be utilized for improved classifier performance. LÄS MER
5. Fake Mass-Produced Advertisements Detection on Global Online Adult Service Websites
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : A significant amount of sex trafficking victims are being advertised on online adult services, which are currently being flooded with spam. Investigators rely on online adult services to track cases of sex trafficking; however, the ever-increasing volume of spam poses a mounting challenge, making their task progressively more difficult. LÄS MER
