Star Ratings versus Sentiment Analysis -- A Comparison of Explicit and Implicit Measures of Opinions

Lak, Parisa; Turetken, Ozgur

doi:10.1109/hicss.2014.106

Cited by 44 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We used a sentiment analysis service provided by Lexalytics (https://www.lexalytics.com/) to assign a continuous sentiment score ranging from 1 to −1 to each document (i.e., Weibo post). Lexalytics has performed satisfactorily compared with other popular sentiment annotation tools (34), such as OpinionFinder and Sentistrength. Lexalytics uses part-of-speech tagging to identify adjective-noun combinations, and then counts the number of affective words in a sentence.…”

Section: Computing Affect Scorementioning

confidence: 99%

Inspecting Vulnerability to Depression From Social Media Affect

2020

View full text Add to dashboard Cite

Affect describes a person's feelings or emotions in reaction to stimuli, and affective expressions were found to be related to depression in social media. This study examined the longitudinal pattern of affect on a popular Chinese social media platform: Weibo. We collected 1,664 Chinese Weibo users' self-reported CES-D scores via surveys and 3 years' worth of Weibo posts preceding the surveys. First, we visualized participants' social media affect and found evidence of cognitive vulnerability indicated by affect patterns: Users with high depression symptoms tended to use not only more negative affective words but also more positive affective words long before they developed early depression symptoms. Second, to identify the type of language that is directly predictive of depression symptoms, we observed ruminations from users who experienced specific life events close to the time of survey completion, and we found that: increased use of negative affective words on social media posts, together with the presence of specific stressful life events, increased a person's risk of developing high depression symptoms; and meanwhile, though tending to focus on negative attributes, participants also incorporated problem-solving skills in their ruminations. These findings expand our understanding of social media affect and its relationship with individuals' risks of developing depression symptoms.

show abstract

Section: Computing Affect Scorementioning

confidence: 99%

Inspecting Vulnerability to Depression From Social Media Affect

2020

View full text Add to dashboard Cite

show abstract

“…The second step dividing the data into training and testing sets, after that extracting the features of user interest from positive movie review as a latent feature [14]. A latent feature like (good movie) can be retrieved by converting the review into its part of speech, then from parsed reviews specify chunks using chunking process, the most critical chunk pattern are:- These extracted chunks are latent features saved as a profile for each user to be used later in clustering process for gathering same users with same latent feature preferences retrieved from their reviews [15].…”

Section: Sentiment Analysis As An Implicit Feedbackmentioning

confidence: 99%

Proposed Collaborative Filtering Recommender System Based on Implicit and Explicit User's Preferences

Hassan

Abdulwahhab

2018

ijs

View full text Add to dashboard Cite

The expansion of web applications like e-commerce and other services yields an exponential increase in offers and choices in the web. From these needs, the recommender system applications have arisen. This research proposed a recommender system that uses user's reviews as implicit feedback to extract user preferences from their reviews to enhance personalization in addition to the explicit ratings. Diversity also improved by using k-furthest neighbor algorithm upon user's clusters. The system tested using Douban movie standard dataset from Kaggle, and show good performance.

show abstract

“…Most of researches about it use text mining method that is sentiment analysis, as in [6], [7], [8], [9], and [10].…”

Section: A Data Variety In Recommendation Systemmentioning

confidence: 99%

“…Interest graph is used to represent secondary entities for any primary entity rated. In [7], there are experiments to mapped sentiment analysis to star rating (1 to 5). The domain of this paper is product review from Amazon.…”

Section: A Data Variety In Recommendation Systemmentioning

confidence: 99%

Public facilities recommendation system based on structured and unstructured data extraction from multi-channel data sources

Putri

Akbar

Sunindyo

2015

2015 International Conference on Data and Software Engineering (ICoDSE)

View full text Add to dashboard Cite

Nowadays social media data has grown very rapidly by producing a huge amount and variety of data everyday. Those data can be analyzed and processed to deliver useful information especially for public needs. However, most of the data available in social media are unstructured. This paper proposes a recommendation system for public facilities by utilizing both structured and unstructured data gathered from multi-channel data sources. The system uses single-criteria rating, multi-criteriarating, and text data as the inputs. The challenge is how to handle data variety such that any kind of data from any channel can be integrated. The second challenge is how to extract location-related data from the raw data. There are four data channels used in the system. Three of them are social media channels, i.e. Twitter, Instagram, and Foursquare, while the other is internal data channel built as a part of the system itself. The system deals with three categories of public facility, i.e. park, hospital, and mosque. The whole system consists of two sub systems, i.e. the extractor system including the rating input module and the recommendation system. The recommendation system is implemented as end-user mobile application such that the users are able to use it anytime and anywhere. The system successfully integrate data from different social media channels and in different format to provide users with useful information concerning public facilities in the form of recommendation (rating) and popularity of the facilities. The experiment has shown that above 90% of the data collected from the social media contains location-related information that is useful for further processing. The system has been tested using usability test, and it obtained an average users score 3.9 on a scale of 1 to 5.

show abstract

Star Ratings versus Sentiment Analysis -- A Comparison of Explicit and Implicit Measures of Opinions

Cited by 44 publications

References 20 publications

Inspecting Vulnerability to Depression From Social Media Affect

Inspecting Vulnerability to Depression From Social Media Affect

Proposed Collaborative Filtering Recommender System Based on Implicit and Explicit User's Preferences

Public facilities recommendation system based on structured and unstructured data extraction from multi-channel data sources

Contact Info

Product

Resources

About