Sökning: "dictionary learning"
Visar resultat 1 - 5 av 44 uppsatser innehållade orden dictionary learning.
1. Understanding Sales Performance Using Natural Language Processing - An experimental study evaluating rule-based algorithms in a B2B setting
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Natural Language Processing (NLP) is a branch in data science that marries artificial intelligence with linguistics. Essentially, it tries to program computers to understand human language, both spoken and written. Over the past decade, researchers have applied novel algorithms to gain a better understanding of human sentiment. LÄS MER
2. Analysing CSR reporting over the years, company size, region, and sector through dictionary-based text mining
Master-uppsats, Högskolan Dalarna/Institutionen för information och teknikSammanfattning : As Corporate Social Responsibility (CSR) reports become more prevalent and systematised, there is a strong need to develop approaches that seek to analyse the contents of these reports. In this thesis, we present two valuable contributions. LÄS MER
3. A Hybrid Approach to Hate Speech Detection
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : An interesting question is to what extent can background knowledge help in the context of text classification. To address this in more detail, can a traditional rulebased classifier help boost the accuracy of learned models? We explore this here for detecting hate speech and offensive language in online text. LÄS MER
4. Narratives in Central Banking - A Case Study on Federal Reserve Communication
C-uppsats, Handelshögskolan i Stockholm/Institutionen för nationalekonomiSammanfattning : This paper investigates how Federal Reserve communication affects financial markets. This is done by constructing a sentiment index based on meeting minutes released by the Federal Open Market Committee. LÄS MER
5. Do central bank speeches help predict monetary policy?
Magister-uppsats, Lunds universitet/Nationalekonomiska institutionen; Lunds universitet/Statistiska institutionenSammanfattning : This paper studies the information contained in central bank speeches, focusing on predicting future monetary policy. Departing from previous papers which use mainly dictionary-based methods, we employ the deep transfer learning technique to process the text data. LÄS MER