A Lexical and Machine Learning-Based Hybrid System for Sentiment Analysis

Mumtaz, Deebha; Ahuja, Bindiya

doi:10.1007/978-981-10-4555-4_11

Cited by 12 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section deals with the results obtained. Result will be analyzed with the help of confusion matrix [4]. In the given matrix sum of P' and N' is always equal to the sum of P and N. Table 2 represents the distinct parameters that are used in the research.…”

Section: Resultsmentioning

confidence: 99%

“…It is ordinarily utilized in client emotionally supportive networks to make an association or framework increasingly productive and compelling by utilizing quicker or more straightforward working strategies. [4] viewed and expected a methodology presenting a combined form of lexical-based and machine learning approach. Combination proposed provides high amount of accuracy than the classical-type of lexical method and it helps in providing the enhanced form of redundancy than the approach of machine learning.…”

Section: Intent Analysismentioning

confidence: 99%

“…This has a major effect on the movie rating. During the data processing phase, links, usernames, punctuation marks, and the same sentences in related tweets were removed [4]. In addition, all words were converted to lower case.…”

Section: Programming Language Usedmentioning

confidence: 99%

See 2 more Smart Citations

Performance Modeling of Classification Techniques on Movie Sentiments

Rani,

Singh

2019

IJEAT

View full text Add to dashboard Cite

The sentiment-based social media represents a goldmine approach for analyzing the performance of the products, hotels, movies, politics, etc. Large opinions of the people are found over movie comments that are honest, informative, and casual as compared to the formal type of data-survey modeling using magazines or reports. The work proposed is based on the rating of movies. This paper analyzes the performance of classifiers for the prediction of sentiment class i.e., positive and negative by using artificial neural network, k-nearest neighbor and hybrid approach. The success of these classification techniques depends mainly on the appropriate extraction of the set of characteristics used to detect sentiments. Hybrid of two or more classifiers is mainly used to enhance the results. In the proposed experiment Hybrid of ANN and KNN shows improvement in precision and accuracy than other classifiers.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Intent Analysismentioning

confidence: 99%

See 1 more Smart Citation

Performance Modeling of Classification Techniques on Movie Sentiments

Rani,

Singh

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…As our dataset is manually annotated (i.e., labeled as positive or negative) we opt for supervised machine learning approach to perform SA. Sentiment Analysis can be performed at the following three levels [12,13]: (i) Document-level: Sentiment Analysis at this level is used to identify the polarity of a single entity in the given document. Document-level sentiment analysis assumes that each document expresses opinions only on a separate body, e.g., a single product or service and is expressed by a single opinion holder.…”

Section: Sentiment Analysismentioning

confidence: 99%

“…An Automatic Seed Word Selection method [17] was proposed for unsupervised sentiment classification of product reviews in Chinese. The lexical-based and machine learning-based approaches are combined in [13] with the aim of introducing a hybrid architecture with higher accuracy than the pure lexical method and provides more structure and increased redundancy than machine learning approach. The Senti-lexical algorithm [9] to find the polarity of a review as positive, negative or neutral is proposed to handle words which have negation effect on the reviews.…”

Section: Literature Reviewmentioning

confidence: 99%

Opinion Mining of GST Implementation using Supervised Machine Learning Approach

Tomar¹,

Srivastava²,

Ahuja³

2018

IJCA

Self Cite

View full text Add to dashboard Cite

Sentiment Analysis is a way to determine the emotions behind social media discussions. Analyzing social data plays a vital role in knowing people"s behavior about an entity or event occurring in the society. Sentiment analysis is widely used in a variety of applications like classifying, summarizing and aggregating reviews from the massive amount of unstructured data that may be available from customer comments, blogs, feedback and reviews on any product or social issue. The Goods & Service Tax(GST) was debated a lot in the social network as it impacts every citizen of India and there was a state of confusion among people about this amendment in the taxation system. If this state of people can be determined, then it can help in identifying how effectively GST scheme is executing. In this paper, we present Sentiment Analysis (SA) of GST by using the textual content of Twitter to determine the public opinion about GST.

show abstract