Tweelyzer. An Approach to Sentiment Analysis of Tweets
-
- Einzelkauf Download ausgewählt
-
Sprache:Englisch
29,99 €
inkl. gesetzl. MwSt.Beschreibung
Produktdetails
Format
Kopierschutz
Nein
Family Sharing
Nein
Text-to-Speech
Nein
Erscheinungsdatum
06.10.2016
Verlag
Anchor Academic PublishingSeitenzahl
79 (Printausgabe)
Dateigröße
10951 KB
Auflage
1. Auflage
Sprache
Englisch
EAN
9783960675907
The ongoing trend of people using microblogging to express their thoughts on various topics has increased the need for developing computerised techniques for automatic sentiment analysis on texts that do not exceed 200 characters. Twitter is a "micro-blogging" social networking site that has a large and rapidly growing base of users. Twitter's tweets or messages are limited to 140 characters. Because of this limitation, it is more difficult to express sentiment and the classification of the tweets is difficult as well. Sentiment analysis can be done on two types: emotion and opinion. This research completely focuses on sentiment analysis of opinions. These opinions can be divided in three different classes: positive, negative and neutral ( somewhere between positive and negative).
The main goal of this study is to build a model that predicts election movement and provide sentiment score from Twitter messages (which can not exceed 140 characters). In this project, the author applies a novel approach that classifies sentiment and emotions of Twitter tweets automatically in positive, negative or neutral classes. For the sentiment, first of all, tweets from twitter were retrieved and converted into the dataset. After pre-processing the data the proposed algorithm named TWEELYZER was applied to the dataset. At the end, the performance of TWEELYZER was measured in terms of accuracy and recall.
In this project, all tweets of people regarding to movies, brands, actors and actresses were collected from twitter and then cleaned and analysed according to the proposed algorithm. These tweets were collected using R Studio software. Several processes took place in pre-processing the tweets. After pre-processing the data, using R Studio led to several insights.
The main goal of this study is to build a model that predicts election movement and provide sentiment score from Twitter messages (which can not exceed 140 characters). In this project, the author applies a novel approach that classifies sentiment and emotions of Twitter tweets automatically in positive, negative or neutral classes. For the sentiment, first of all, tweets from twitter were retrieved and converted into the dataset. After pre-processing the data the proposed algorithm named TWEELYZER was applied to the dataset. At the end, the performance of TWEELYZER was measured in terms of accuracy and recall.
In this project, all tweets of people regarding to movies, brands, actors and actresses were collected from twitter and then cleaned and analysed according to the proposed algorithm. These tweets were collected using R Studio software. Several processes took place in pre-processing the tweets. After pre-processing the data, using R Studio led to several insights.
Noch keine Bewertungen vorhanden
Verfassen Sie die erste Bewertung zu diesem Artikel
Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.
Kurze Frage zu unserer Seite
Vielen Dank für dein Feedback
Wir nutzen dein Feedback, um unsere Produktseiten zu verbessern. Bitte habe Verständnis, dass wir dir keine Rückmeldung geben können. Falls du Kontakt mit uns aufnehmen möchtest, kannst du dich aber gerne an unseren Kund*innenservice wenden.
zum Kundenservice