Customer review summarization approach using Twitter and SentiWordNet

Jmal, Jihene; Faiz, Rim

doi:10.1145/2479787.2479813

Cited by 21 publications

(20 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early work by (Hatzivassiloglou, et al, 2000) found that the presence and type of certain terms like adjectives can be used to indicate whether a sentence is being subjective or objective. Other parts of speech have been found to be useful in Sentiment Analysis, such as adverbs ( (Benamara, et al, 2007), (Taboada, et al, 2011)) nouns (Nasukawa, et al, 2003), and verbs (Wiebe, et al, 2004), or all three, ( (Volkova, et al, 2013), (Jmal, et al, 2013), (Subrahmanian, et al, 2008)) as these types of words have been found to play an important role in Sentiment Analysis.…”

Section: Related Workmentioning

confidence: 99%

Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach

Sweeney¹,

Deepak²

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

The sentiment analysis task has been traditionally divided into lexicon or machine learning approaches, but recently the use of word embeddings methods have emerged, that provide powerful algorithms to allow semantic understanding without the task of creating large amounts of annotated test data. One problem with this type of binary classification, is that the sentiment output will be in the form of '1' (positive) or '0' (negative) for the string of text in the tweet, regardless if there are one or more entities referred to in the text. This paper plans to enhance the word embeddings approach with the deployment of a sentiment lexicon-based technique to appoint a total score that indicates the polarity of opinion in relation to a particular entity or entities. This type of sentiment classification is a way of associating a given entity with the adjectives, adverbs, and verbs describing it, and extracting the associated sentiment to try and infer if the text is positive or negative in relation to the entity or entities.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach

Sweeney¹,

Deepak²

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

show abstract

“…For instance, Jmal et al [16] develop a customer review summarization approach which aims to summarize the whole opinion extracted from a huge amount of customer reviews to help business owners in decision making. They measure the polarity strength of the opinion using Twitter and SentiWordNet [3] and then provide scores revealing the customer satisfaction degree for a given product as well as its features instead of just marking whether the opinions are positive or negative.…”

Section: Opinion Summarizationmentioning

confidence: 99%

“…They measure the polarity strength of the opinion using Twitter and SentiWordNet [3] and then provide scores revealing the customer satisfaction degree for a given product as well as its features instead of just marking whether the opinions are positive or negative. Like [16], in our approach, we turn the customer reviews into scores measuring customer satisfaction strength for various products along with their features. Our work differs from theirs in the fact that we will deal with Twitter conversations rather than web reviews.…”

Section: Opinion Summarizationmentioning

confidence: 99%

“…This method is closely similar to the feature detection process employed by [16] which provide feature-based opinion summarization for customer reviews based on product reviews collected via electronic commerce websites and Twitter. The average recall of opinion sentence extraction is nearly 63% while the average precision is around 57%.…”

Section: Feature Detectionmentioning

confidence: 99%

“…The huge volume of conversations produced everyday makes them an interesting information source and valuable tool to discover new trends and exchange opinions and feedbacks towards products, news and stories. A large number of the messages are carriers of opinions and feelings [16,22]. One major field that took advantage of this potential is e-reputation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Customer Opinion Summarization Based on Twitter Conversations

Othman

Belkaroui

Faiz

2016

Proceedings of the 6th International Conference on Web Intelligence, Mining and Semantics

Self Cite

View full text Add to dashboard Cite

As Twitter gains popularity, millions of messages are generated every day via this platform allowing people to communicate with each other through daily chatter and public conversations. This social content is usually considered more subjective than professional articles involving a lot of opinions and thoughts. This has stimulated many companies to use tweets to keep track and have general overview on their customer opinions about the brand. The conversational element of Twitter is of particular interest to the marketing community. However, most studies on summarizing customer opinions through Twitter, have so far employed single tweets rather than considering the whole conversations. As tweets are limited to 140 characters and usually written in an informal way, it is frequently hard to detect the exact meaning of the tweet when taken separately. In this paper, we propose a new approach for customer opinion summarization based on Twitter conversations named COSTwiC. We employ a new conversation-based method that employs conversation interactions to effectively extract the different product features as well as the polarity of the conversation messages. Experimentations show promising results. In particular, we have proved that incorporating conversation structure in the opinion summarization task contributes to improving system performance.

show abstract

Aspect and Sentiment Unification Model for Twitter Analysis

Zhang

Liu

2015

Intelligence Science and Big Data Engineering. Big Data and Machine Learning Techniques

View full text Add to dashboard Cite

Customer review summarization approach using Twitter and SentiWordNet

Cited by 21 publications

References 20 publications

Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach

Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach

Customer Opinion Summarization Based on Twitter Conversations

Aspect and Sentiment Unification Model for Twitter Analysis

Contact Info

Product

Resources

About