BUAP: Polarity Classification of Short Texts
نویسندگان
چکیده
We report the results we obtained at the subtask B (Message Polarity Classification) of SemEval 2014 Task 9. The features used for representing the messages were basically trigrams of characters, trigrams of PoS and a number of words selected by means of a graph mining tool. Our approach performed slightly below the overall average, except when a corpus of tweets with sarcasm was evaluated, in which we performed quite well obtaining around 6% above the overall average.
منابع مشابه
Minería de opiniones centrada en tópicos usando textos cortos en español
Users express their feelings about an entity of a specific topic in a free way using short texts on social networks. Sentiment analysis, also known as opinion mining, focuses on examining these texts to determine their polarity. This article presents an approach to the mining of opinions based on topics from Twitter texts in Spanish. The main objective is to decide the polarity of a text, deter...
متن کاملRobust Compositional Polarity Classification
We describe a pattern-based system for polarity classification from texts. Our system is currently restricted to the positive, negative or neutral polarity of phrases and sentences. It analyses the input texts with the aid of a polarity lexicon that specifies the prior polarity of words. A chunker is used to determine phrases that are the basis for a compositional treatment of phrase-level pola...
متن کاملImproving Web 2.0 Opinion Mining Systems Using Text Normalisation Techniques
A basic task in opinion mining deals with determining the overall polarity orientation of a document about some topic. This has several applications such as detecting consumer opinions in on-line product reviews or increasing the effectiveness of social media marketing campaigns. However, the informal features of Web 2.0 texts can affect the performance of automated opinion mining tools. These ...
متن کاملRecognizing Polarity and Attitude of Words in Text
In this work, we present a problem of Sentiment Classification in texts. Sentiment Classification is an Opinion Mining and Sentiment Analysis task that has opened several problems, including a significant variety of applications. We propose a strategy to distinguish words that convey evaluation of an item from the rest, as well as to classify the evaluation polarity (positive or negative). In a...
متن کاملSingle and Cross-domain Polarity Classification using String Kernels
The polarity classification task aims at automatically identifying whether a subjective text is positive or negative. When the target domain is different from those where a model was trained, we refer to a cross-domain setting. That setting usually implies the use of a domain adaptation method. In this work, we study the single and cross-domain polarity classification tasks from the string kern...
متن کامل