Context Deployed Sentiment Analysis Using Hybrid Lexicon

John, Annet; John, Anice; Sheik, Reshma

doi:10.1109/iciict1.2019.8741413

Cited by 15 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…obtained sentiment scores from SentiWordNet to use in their opinion-mining application by creating movie scores from blog pages [ 58 ]. proposed a four-step approach as sentiment word detection, sentiment shifter detection, sentiment score handling, and aggregated score calculation for aspect-sentiment matching on customer reviews of products [ 59 ]. performed hybrid lexicon-based sentiment analysis on tweet data with their polarities gained from Sentiment140.com .…”

Section: Related Workmentioning

confidence: 99%

Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers

Cam,

Demirel

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers

Cam,

Demirel

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…They also suggested that it might associate with prosodic indicators, which are commonly used in verbal communication. John et al (2019) suggested that including character repetition and word capitalization to a sentiment classification model gain a substantial improvement. These studies support our hypothesis that misspelling has inherent semantics that correlates with the sentiment of a sentence.…”

Section: Related Workmentioning

confidence: 99%

Misspelling Semantics In Thai

Nakwijit¹,

Purver²

2022

Preprint

View full text Add to dashboard Cite

User-generated content is full of misspellings. Rather than being just random noise, we hypothesise that many misspellings contain hidden semantics that can be leveraged for language understanding tasks. This paper presents a fine-grained annotated corpus of misspelling in Thai, together with an analysis of misspelling intention and its possible semantics to get a better understanding of the misspelling patterns observed in the corpus. In addition, we introduce two approaches to incorporate the semantics of misspelling: Misspelling Average Embedding (MAE) and Misspelling Semantic Tokens (MST). Experiments on a sentiment analysis task confirm our overall hypothesis: additional semantics from misspelling can boost the micro F1 score up to 0.4-2%, while blindly normalising misspelling is harmful and suboptimal.

show abstract

“…Although sentiment analysis has achieved astounding successes across a wide range of domains, nevertheless there are several challenges associated with its real‐time implementation. The most pertinent issue in any sentiment analysis task is the resolution of the context 10‐14 . The process of enabling machines to analyze the connotation of words, slang, cultural diversities, and spelling mistakes that frequently occur in text documents are extremely complex and challenging tasks.…”

Section: Introductionmentioning

confidence: 99%

“…The most pertinent issue in any sentiment analysis task is the resolution of the context. [10][11][12][13][14] The process of enabling machines to analyze the connotation of words, slang, cultural diversities, and spelling mistakes that frequently occur in text documents are extremely complex and challenging tasks. Opinion mining through sentiment analysis of textual documents is a tedious task even for human beings who are blessed with intuitions; let alone for machines that know nothing about the intricacies of human languages.…”

Section: Introductionmentioning

confidence: 99%

A heterogeneous stacking ensemble based sentiment analysis framework using multiple word embeddings

Subba

Kumari

2021

Computational Intelligence

View full text Add to dashboard Cite

Word embedding techniques have been proposed in the literature to analyze and determine the sentiments expressed in various textual documents such as social media posts, online product reviews, and so forth. However, it is difficult to capture the entire gamut of intricate inter-dependencies among words in the textual documents using a specific word embedding technique. In this article, we aim to address this issue by proposing a computation-efficient stacking ensemble based sentiment analysis framework using multiple word embeddings. The proposed framework uses a combination of three distinct word embeddings generated by three different state of the art word embedding techniques, namely, Word2Vec, GloVe, and BERT for performing the sentiment analysis task. It uses an explicitly trained Word2Vec model to generate the first set of 200-dimensional word embedding. Similarly, pre-trained GloVe and BERT models are used to generate the other two sets of 200-dimensional and a 768-dimensional word embeddings, respectively. These three distinct word embedding sets are then used to train a heterogeneous stacking ensemble based classifier model comprising LSTM, GRU, and Bi-GRU based base-level classifiers, and a LSTM based meta-level classifier. Experimental results on four different datasets, 530

show abstract

Context Deployed Sentiment Analysis Using Hybrid Lexicon

Cited by 15 publications

References 9 publications

Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers

Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers

Misspelling Semantics In Thai

A heterogeneous stacking ensemble based sentiment analysis framework using multiple word embeddings

Contact Info

Product

Resources

About