Extracting Gamers' Opinions from Reviews

Sirbu, Dorinela; Secui, Ana; Dascălu, Mihai; Crossley, Scott A.; Ruşeţi, Ştefan; Trăușan-Matu, Ștefan

doi:10.1109/synasc.2016.044

Cited by 9 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods that construct new features from existing ones are known as feature transformation methods. Techniques include principal component analysis (PCA; Sirbu et al, 2016 ; Zu, Ohyama, Wakabayashi, & Kimura, 2003 ), latent semantic analysis (LSA; Landauer et al, 1998 ), and nonnegative matrix factorization ( Zurada, Ensari, Asl, & Chorowski, 2013 ). These methods construct high level features as a (non)linear combination of the original features with the property that the new features are uncorrelated.…”

Section: Tc: the Processmentioning

confidence: 99%

Text Classification for Organizational Researchers

Kobayashi

Mol

Berkers

et al. 2017

Organizational Research Methods

View full text Add to dashboard Cite

Organizations are increasingly interested in classifying texts or parts thereof into categories, as this enables more effective use of their information. Manual procedures for text classification work well for up to a few hundred documents. However, when the number of documents is larger, manual procedures become laborious, time-consuming, and potentially unreliable. Techniques from text mining facilitate the automatic assignment of text strings to categories, making classification expedient, fast, and reliable, which creates potential for its application in organizational research. The purpose of this article is to familiarize organizational researchers with text mining techniques from machine learning and statistics. We describe the text classification process in several roughly sequential steps, namely training data preparation, preprocessing, transformation, application of classification techniques, and validation, and provide concrete recommendations at each step. To help researchers develop their own text classifiers, the R code associated with each step is presented in a tutorial. The tutorial draws from our own work on job vacancy mining. We end the article by discussing how researchers can validate a text classification model and the associated output.

show abstract

Section: Tc: the Processmentioning

confidence: 99%

Text Classification for Organizational Researchers

Kobayashi

Mol

Berkers

et al. 2017

Organizational Research Methods

View full text Add to dashboard Cite

show abstract

“…As a final remark, we compare our results with the results obtained on the same dataset in [48] and in [40]. Our proposed Deep Neural Network architectures outperform with ∼10% the Transformer-based models in [40] that obtained an accuracy of only 0.67.…”

Section: Resultsmentioning

confidence: 75%

Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

et al. 2021

View full text Add to dashboard Cite

Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without considering the local context that can be extracted from the dataset, or they detect the overall topic polarity without considering both the local and global context. In this paper, we propose a novel document-topic embedding model, DocTopic2Vec, for document-level polarity detection in large texts by employing general and specific contextual cues obtained through the use of document embeddings (Doc2Vec) and Topic Modeling. In our approach, (1) we use a large dataset with game reviews to create different word embeddings by applying Word2Vec, FastText, and GloVe, (2) we create Doc2Vecs enriched with the local context given by the word embeddings for each review, (3) we construct topic embeddings Topic2Vec using three Topic Modeling algorithms, i.e., LDA, NMF, and LSI, to enhance the global context of the Sentiment Analysis task, (4) for each document and its dominant topic, we build the new DocTopic2Vec by concatenating the Doc2Vec with the Topic2Vec created with the same word embedding. We also design six new Convolutional-based (Bidirectional) Recurrent Deep Neural Network Architectures that show promising results for this task. The proposed DocTopic2Vecs are used to benchmark multiple Machine and Deep Learning models, i.e., a Logistic Regression model, used as a baseline, and 18 Deep Neural Networks Architectures. The experimental results show that the new embedding and the new Deep Neural Network Architectures achieve better results than the baseline, i.e., Logistic Regression and Doc2Vec.

show abstract

“…Zhu and Fang [ 61 ] explored games’ online reviews to characterise games and play-ability; their work used a lexical approach adapted from instruments which are generally used by psychologists in studying personality traits. Sirbu et al [ 46 ] used opinion mining to better understand players’ feelings from reviews and classify them into positive, negative and neutral reviews.…”

Section: Introductionmentioning

confidence: 99%

An opinion mining methodology to analyse games for health

Silva

Santos

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Despite the positive impact of games for health on players’ health, users tend to stop playing them after a short period of time, leading benefits to fade. It is therefore important to understand how to sustain interest and, in this way, preserve the health benefits of games for health. This could be achieved by continuously reviewing user feedback after product launch and using this information to inform (re)design and better address user needs. With the growth of social media, user opinions became widely available in public forums. This abundance of information affords us the possibility of, through the application of natural language processing and sentiment analysis techniques, tapping into user opinions and automatically analysing and extracting knowledge from them. This paper introduces a methodology that analyses user comments posted on YouTube about the Just Dance game, to automatically extract information about Usability, User Experience (UX), and Perceived Health Impacts related to Quality of Life (H-QoL). In doing so, the methodology uses a pre-established vocabulary, based on the English lexicon and its semantic relations, to annotate the presence of 38 concepts (five of Usability, 18 of UX, and 15 of H-QoL) and to analyse sentiment. The results of the information extraction and processing are displayed on a dashboard that allows for the exploration and browsing of the results, which can be useful to better understand the opinions and impacts perceived by users and to inform the (re)design of games for health. The methodology proposed builds upon over 500,000 user comments collected from over 32,000 videos.

show abstract

Extracting Gamers' Opinions from Reviews

Cited by 9 publications

References 14 publications

Text Classification for Organizational Researchers

Text Classification for Organizational Researchers

Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

An opinion mining methodology to analyse games for health

Contact Info

Product

Resources

About