Sentiment analysis of product reviews: A review

Shivaprasad, T. K.; Shetty, Jyothi

doi:10.1109/icicct.2017.7975207

Cited by 68 publications

(31 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The rundown ought to be browsed the arrangement of items connected. A few examinations outline forecasts of purchasing conduct in employment grouping [7,10] that require statistic attributes of clients, for example, age, sexual orientation, instruction and occupation. In contrast to customary organizations, organizations in the web based business setting think that its hard to get data about statistic data or family foundation in light of the fact that these information are regularly viewed as close to home data.…”

Section: Related Workmentioning

confidence: 99%

“…In a UserBasedRecommender [9], a User Neighborhood selects users that act as a jury for finding items to recommend. Due to its simplicity and scalability, the item-based approach [8,10] represents the most widely deployed recommendation algorithm. It can present the items most similar to a given item (a popular non-personalized way of recommending) and can provide preferences for items as justification for recommendations.…”

Section: Fig 3 Recommendation Process In Mahoutmentioning

confidence: 99%

See 1 more Smart Citation

Aspect Based Mobile Recommendation System

Bawiskar¹,

Injamuri²

2019

IJITEE

View full text Add to dashboard Cite

Now-a-days, there is a trend of changing mobile phone models in very short duration. To achieve benefit of choosing a mobile phone satisfying our requirements, mobile phone recommendation system is of great importance. As we know, there are many web sites that provide number of reviews and ratings for each and every mobile phone model available in market. From this, we can understand the consumer opinions and reviews about any mobile product. Existing systems were based on complete review of product as good or bad. But, there is need to have a way with which we can review the product with view of each aspect such as camera, battery, look etc. For this, we have developed a system which provides a recommendation of mobile phone model by considering aspects with user’s choice. For this, we have used reviews, ratings provided by group of users on social website, Amazon. The data is collected with the use of “Octoparse”, a web scraping software and the text data collected is analyzed using Stanford's CoreNLP for sentiment analysis. Our approach provides recommendation, considering user provided aspects (i.e. camera, battery, look etc.) with the use of apache mahout and hybrid recommendation. Our approach showed outstanding performance for mobile phone recommendation

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Fig 3 Recommendation Process In Mahoutmentioning

confidence: 99%

Aspect Based Mobile Recommendation System

Bawiskar¹,

Injamuri²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…Support Vector Machine is a non-probabilistic supervised learning approach where we train a machine by training dataset which labels data and divides them into different classes [26]. When new data is fed into the machine, the algorithm assigns it the labels and divides it into respective classes.…”

Section: Svmmentioning

confidence: 99%

Emotion detection on cross platform languages

Arif

Singh

Boparai

2018

IJET

View full text Add to dashboard Cite

Internet has changed the course of our living. It has become the most beneficial antecedent or source of information. Today almost everything is found on internet. Everyday millions of people post their ideas, reviews, stories about the services, products or other persons. The size of data is increasing tremendously. It is very difficult to analyze that amount of data and figure out the emotions or sentiments posed by people. Emotion detection is such a technique where we can judge people’s ideas and extract the emotion towards an entity or service. We have used subjective lexicon-based approach to bench the emoticons expressed by the ideas of the people. The data set that we have mainly focused is very cross and noisy. We have used Facebook data in Urdu and Kashmiri language. Both languages are very cross domain. These languages can be written in English alphabet that makes them more challenging to analyses. Our approach resolves the challenge to the maximum possible way. The results shown by our method on this kind of data set are better than any other approach. Our analysis on this type of dataset will help the local businessmen of these areas to grow and flourish. The analysis will give some insights what the local feel about the entity or product so that the manufacturers can design or build it that way and try to enhance its qualities.

show abstract

“…Search engines run NLP algorithms on web pages through a process called crawling and index web pages with associated keywords so as to enable them to respond to user search queries based on keywords [11][12][13]. Sentiment analysis NLP techniques have been used to automate the process of accessing product reviews and comments on e-commerce sites [14,15]. NLP based chatbots have also been developed in an attempt to provide automated customer support in e-commerce and the like industries [16].…”

Section: Introductionmentioning

confidence: 99%

AI and data-driven Christian Theology

S¹

2020

Preprint

View full text Add to dashboard Cite

An NLP based AI tool was developed for topic mining Christian writings of major figures from different Christian eras and movements. The text corpus chosen for text mining includes : the volumes of Augustine and John Chrysostom from the patristic period, the writings of Thomas Aquinas from the Scholastic period, the writings of John Calvin the reformer and the text corpus of sermons by George Whitefield and John Wesley that mark the beginning of the modern Christian evangelical movement and evangelicalism. The topics text mined and topics summarized include : Gospel, Salvation, Jesus Christ, Sin, Temptation, Tribulation, Pride, Lust, Envy, Joy, Hope, Charity, Marriage, Church, Heaven, Hell. They are downloadable from the link - https://drive.google.com/drive/folders/1tG2Y36MF1ApvYnhPM_njtNvKYiv7_8RL?usp=sharing and this is expected to help Christian content developers. The link to the code of the NLP tool hosted in the GitHub repository is provided to aid further development - https://github.com/bengeof/AI-driven-Theology-Open-Development. These tools must not be viewed as threatening the role of the human in humanities research broadly and specifically in Christian theology but as empowering the human with additional powers of AI for research in the humanities in the age of Big Data.

show abstract

Sentiment analysis of product reviews: A review

Cited by 68 publications

References 7 publications

Aspect Based Mobile Recommendation System

Aspect Based Mobile Recommendation System

Emotion detection on cross platform languages

AI and data-driven Christian Theology

Contact Info

Product

Resources

About