Improving Twitter Sentiment Analysis with Topic-Based Mixture Modeling and Semi-Supervised Training

Xiang, Bing; Zhou, Liang

doi:10.3115/v1/p14-2071

Cited by 71 publications

(50 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…So the training and testing dataset is downloaded from http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html, training dataset consist of total 6828 positive and negative words. Testing data set contain free text reviews written by user towards particular product [8]. Figure2 shows system architecture which is divided into two phase .Training phase and testing phase.…”

Section: Methodsmentioning

confidence: 99%

“…In this system using Machine learning approach which is divided into supervised ,unsupervised and semi supervised methods [8].Here supervised classification is being implemented which requires training and testing dataset. So the training and testing dataset is downloaded from http://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html, training dataset consist of total 6828 positive and negative words.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identifying and Ranking Dominating Product Features using NLP Technique

Ingale¹,

Deshmukh²

2015

IJCA

View full text Add to dashboard Cite

As internet usage increased users uses internet not only to access and search information but also at the same time able to spread and publish own idea, sentiments, knowledge via different number of websites. Different websites encourage their user to write their views in the form of electronic text. This system increasing user-written electronic text in the world of internet, large numbers of user opinions are available on World Wide Web. User review contains important information, which is beneficial for customer as well as retailer. These reviews are in scattered format so extracting important data from this large corpus is time consuming work. Here developing a system which will automatically identify and rank the product features. The Stanford parser is used for identify product features. Sentence level sentiment classification is used for identify sentiment of each sentence separately, Sentiment Classifier is used for classifying each sentence, and finally a probabilistic ranking algorithm is used to rank the product features.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Identifying and Ranking Dominating Product Features using NLP Technique

Ingale¹,

Deshmukh²

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…Characterizing an attitude as positive, negative or neutral toward a topic is known as sentiment analysis. Most of the contribution in the field focuses on finding sentiments in the tweet level [1,5,13,25], some of them suggest aggregating the sentiments as a simple sum [4,7,17,22,24], while the problem of the reputation of an entity has not been specifically addressed. Natural language processing is a well-established research area in computer science.…”

Section: Related Workmentioning

confidence: 99%

“…Machine learning techniques prove to be effective with sentiment analysis: a semi-supervised approach that uses an interpolation between a universal labeled training set as a base, processed with SVM, and then a topic-related unlabeled training set for enrichment, processed with LDA in [25] and naive Bayes that uses topic-related clusters in [22]. In order to augment the accuracy of the classifier, semantic sentiment analysis is used in [19].…”

Section: Related Workmentioning

confidence: 99%

A Frequent Named Entities-Based Approach for Interpreting Reputation in Twitter

et al. 2018

View full text Add to dashboard Cite

Twitter is a social network that provides a powerful source of data. The analysis of those data offers many challenges among those stands out the opportunity to find reputation of a product, a person or any other entity of interest. Several approaches for sentiment analysis have been proposed in the literature to assess the general opinion expressed in tweets on an entity. Nevertheless, these methods aggregate sentiment scores retrieved from tweets, which is a static view to evaluate the overall reputation of an entity. The reputation of an entity is not static; entities collaborate with each other, and they get involved in different events over time. A simple aggregation of sentiment scores is then not sufficient to represent this dynamism. In this paper, we present a new approach to determine the reputation of an entity on the basis of the set of events in which it is involved. To achieve this, we propose a new sampling method driven by a tweet weighting measure to give a better quality and summary of the target entity. We introduce the concept of Frequent Named Entities to determine the events involving the target entity. Our evaluation achieved for different entities shows that 90% of the reputation of an entity originates from the events it is involved in and the breakdown into events allows interpreting the reputation in a transparent and self-explanatory way.

show abstract

“…The paper by Tang et al [27] shows a joint sentence-level segmentation and classification system. Latent Dirichlet Allocation (LDA) was used by Xiang and Zhou [28] in the creation of topic-specific information, before going on to divide the data into several subsets based on topic distribution. In the last wave, they presented a semi-supervised training system to further increase classification accuracy.…”

Section: A Sentiment Analysis In Genaralmentioning

confidence: 99%

Arabic Sentiment Analysis: A Survey

Assiri¹,

Emam²,

Al-Dossari³

2015

ijacsa

View full text Add to dashboard Cite

Abstract-Most social media commentary in the Arabic language space is made using unstructured non-grammatical slang Arabic language, presenting complex challenges for sentiment analysis and opinion extraction of online commentary and micro blogging data in this important domain. This paper provides a comprehensive analysis of the important research works in the field of Arabic sentiment analysis. An in-depth qualitative analysis of the various features of the research works is carried out and a summary of objective findings is presented. We used smoothness analysis to evaluate the percentage error in the performance scores reported in the studies from their linearly-projected values (smoothness) which is an estimate of the influence of the different approaches used by the authors on the performance scores obtained. To solve a bounding issue with the data as it was reported, we modified existing logarithmic smoothing technique and applied it to pre-process the performance scores before the analysis. Our results from the analysis have been reported and interpreted for the various performance parameters: accuracy, precision, recall and F-score.

show abstract

Improving Twitter Sentiment Analysis with Topic-Based Mixture Modeling and Semi-Supervised Training

Cited by 71 publications

References 13 publications

Identifying and Ranking Dominating Product Features using NLP Technique

Identifying and Ranking Dominating Product Features using NLP Technique

A Frequent Named Entities-Based Approach for Interpreting Reputation in Twitter

Arabic Sentiment Analysis: A Survey

Contact Info

Product

Resources

About