Stage-oe-small.jpg

Thema4595: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
K
 
(Eine dazwischenliegende Version desselben Benutzers wird nicht angezeigt)
Zeile 5: Zeile 5:
 
|Partner=FIZ Karlsruhe
 
|Partner=FIZ Karlsruhe
 
|Forschungsgruppe=Information Service Engineering
 
|Forschungsgruppe=Information Service Engineering
|Abschlussarbeitsstatus=Offen
+
|Abschlussarbeitsstatus=Vergeben
 
|Beginn=2020/05/01
 
|Beginn=2020/05/01
 +
|Ausschreibung=Concept-level Sentiment Analysis with  SenticNet and Word Embeddings.pdf
 
|Beschreibung DE=Sentiment Analysis is an extremely difficult task as it requires the understanding and interpretation of data. Humans can do it, machines cannot. To close this gap, word statistics to compute a positive/negative polarity of texts, or word embedding representations which can somehow embed emotional information have been recently investigated. These representations are used to feed Machine Learning algorithms with the hope that they learn patterns and predicts correct sentiment labels.
 
|Beschreibung DE=Sentiment Analysis is an extremely difficult task as it requires the understanding and interpretation of data. Humans can do it, machines cannot. To close this gap, word statistics to compute a positive/negative polarity of texts, or word embedding representations which can somehow embed emotional information have been recently investigated. These representations are used to feed Machine Learning algorithms with the hope that they learn patterns and predicts correct sentiment labels.
 
However, these approaches lack concept-level semantics which allows us to go beyond a mere word analysis. Concept-level sentiment analysis steps away from blind us of words, but rather tries to adopt features associated to natural language concepts. The goal of the thesis is to study how SenticNet [1] resources, which contain emotional information about concepts, can be used in combination with word embedding representations (e.g., word2vec, fasttext, BERT) for sentiment analysis tasks. The approach will be applied for score prediction on learners’ reviews of the Coursera dataset [2].
 
However, these approaches lack concept-level semantics which allows us to go beyond a mere word analysis. Concept-level sentiment analysis steps away from blind us of words, but rather tries to adopt features associated to natural language concepts. The goal of the thesis is to study how SenticNet [1] resources, which contain emotional information about concepts, can be used in combination with word embedding representations (e.g., word2vec, fasttext, BERT) for sentiment analysis tasks. The approach will be applied for score prediction on learners’ reviews of the Coursera dataset [2].

Aktuelle Version vom 30. Juni 2020, 13:55 Uhr



Concept-level Sentiment Analysis with SenticNet and Word Embeddings




Informationen zur Arbeit

Abschlussarbeitstyp: Master
Betreuer: Danilo DessiHarald Sack
Forschungsgruppe: Information Service Engineering
Partner: FIZ Karlsruhe
Archivierungsnummer: 4595
Abschlussarbeitsstatus: Vergeben
Beginn: 01. Mai 2020
Abgabe: unbekannt

Weitere Informationen

Sentiment Analysis is an extremely difficult task as it requires the understanding and interpretation of data. Humans can do it, machines cannot. To close this gap, word statistics to compute a positive/negative polarity of texts, or word embedding representations which can somehow embed emotional information have been recently investigated. These representations are used to feed Machine Learning algorithms with the hope that they learn patterns and predicts correct sentiment labels. However, these approaches lack concept-level semantics which allows us to go beyond a mere word analysis. Concept-level sentiment analysis steps away from blind us of words, but rather tries to adopt features associated to natural language concepts. The goal of the thesis is to study how SenticNet [1] resources, which contain emotional information about concepts, can be used in combination with word embedding representations (e.g., word2vec, fasttext, BERT) for sentiment analysis tasks. The approach will be applied for score prediction on learners’ reviews of the Coursera dataset [2]. [1] https://sentic.net/downloads/ [2] https://www.kaggle.com/septa97/100k-courseras-course-reviews-dataset

The thesis will be supervised by Prof. Dr. Harald Sack, Information Service Engineering at Institute AIFB, KIT, in collaboration with FIZ Karlsruhe.

Pre-requisites: Good programming skills in Python, creativity, curiosity, and willingness to learn


Ausschreibung: Download (pdf)