Sentiment Analysis of Short Informal Texts

Abstract

We describe a state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the sentiment of a word or a phrase within a message (term-level task). The system is based on a supervised statistical text classification approach leveraging a variety of surface-form, semantic, and sentiment features. The sentiment features are primarily derived from novel high-coverage tweet-specific sentiment lexicons. These lexicons are automatically generated from tweets with sentiment-word hashtags and from tweets with emoticons. To adequately capture the sentiment of words in negated contexts, a separate sentiment lexicon is generated for negated words. The system ranked first in the SemEval-2013 shared task `Sentiment Analysis in Twitter' (Task 2), obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. Post-competition improvements boost the performance to an F-score of 70.45 (message-level task) and 89.50 (term-level task). The system also obtains state-of-the-art performance on two additional datasets: the SemEval-2013 SMS test set and a corpus of movie review excerpts. The ablation experiments demonstrate that the use of the automatically generated lexicons results in performance gains of up to 6.5 absolute percentage points.

An Empirical Study on the Effect of Negation Words on Sentiment

“…The PSTN model, which takes into account the human-annotated prior sentiment of arguments, performs the best. This could suggest that additional external knowledge, e.g., that from human-built resources or automatically learned from other data (e.g., as in (Kiritchenko et al, 2014)), including sentiment that cannot be inferred from its constituent expressions, might be incorporated to benefit the current neural-network-based models as prior knowledge. Note that the two neural network based models incorporate the syntax and semantics by representing each node with a vector.…”

Sentiment Analysis: It’s Complicated!

“…The popularity of Twitter as a social media platform on which people can readily express their thoughts, feelings, and opinions, coupled with the openness of the platform, provides a large amount of publicly accessible data ripe for analysis, being a well established domain for sentiment analysis as reflecting realworld attitudes (Pak and Paroubek, 2010;Bollen et al, 2011). In this paper, we look into Twitter sentiment analysis (TSA) as a suitable, core instance of general short-text sentiment analysis (Thelwall et al, 2010(Thelwall et al, , 2012Kiritchenko et al, 2014;Dos Santos and Gatti, 2014), and encourage the methods and practices presented to be applied across other domains. Building a TSA model that can automatically determine the sentiment of a tweet has received significant attention over the past several years.…”

TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news

“…There has been considerable research focusing on sentiment analysis of short texts (Thelwall et al, 2010;Kiritchenko et al, 2014), especially within recent SemEval campaigns (Nakov et al, 2016;Rosenthal et al, 2015Rosenthal et al, , 2014. A large body of recent work focuses on sentence-level sentiment prediction.…”