Sentiment analysis from text
Sentiment Analysis Using Dependency Trees and Named-Entities.
There has recently been growing interest in valence and emotion sensing using a variety of signals. Text, as a communication channel, gathers a substantial amount of interest for recognizing its underlying sentiment (valence or polarity), affect or emotion (e.g. happy, sadness).
We consider recognizing the valence of a sentence as a prior task to emotion sensing. In this project, we classify sentences in terms of emotional valence. Our supervised system performs syntactic and semantic analysis for feature extraction. Our system processes the interactions between words in sentences using dependency parse trees, and it can identify the current polarity of named-entities based on on- the-fly topic modeling.
We compared the performance of three rule-based approaches and two supervised approaches (i.e. Naive Bayes and Maximum Entropy). We trained and tested our system using the SemEval-2007 affective text dataset, which contains news headlines extracted from news websites. Our results show that our systems outperform the systems demonstrated in SemEval-2007.
This project is described in more details in the following article:
Ugan Yasavur, Jorge Travieso, Christine Lisetti, Naphtali Rishe. Sentiment Analysis Using Dependency Trees and Named-Entities. In Proceedings of the 27th International FLAIRS Conference, www.aaai.org, (Pensacola Beach, Florida, USA, May 2014) [PDF].
There has recently been growing interest in valence and emotion sensing using a variety of signals. Text, as a communication channel, gathers a substantial amount of interest for recognizing its underlying sentiment (valence or polarity), affect or emotion (e.g. happy, sadness).
We consider recognizing the valence of a sentence as a prior task to emotion sensing. In this project, we classify sentences in terms of emotional valence. Our supervised system performs syntactic and semantic analysis for feature extraction. Our system processes the interactions between words in sentences using dependency parse trees, and it can identify the current polarity of named-entities based on on- the-fly topic modeling.
We compared the performance of three rule-based approaches and two supervised approaches (i.e. Naive Bayes and Maximum Entropy). We trained and tested our system using the SemEval-2007 affective text dataset, which contains news headlines extracted from news websites. Our results show that our systems outperform the systems demonstrated in SemEval-2007.
This project is described in more details in the following article:
Ugan Yasavur, Jorge Travieso, Christine Lisetti, Naphtali Rishe. Sentiment Analysis Using Dependency Trees and Named-Entities. In Proceedings of the 27th International FLAIRS Conference, www.aaai.org, (Pensacola Beach, Florida, USA, May 2014) [PDF].
