Aspect based Sentiment Oriented Summarization of Hotel Reviews

Akhtar, Nadeem; Zubair, Nashez; Abhishek, Kumar; Ahmad, Tameem

doi:10.1016/j.procs.2017.09.115

Cited by 99 publications

(56 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Participants 16.1% as moderately high, 6.4% as somewhat high, 2.34% as not high and 0.6% as not high at all.…”

Section: B Descriptive Statisticsmentioning

confidence: 93%

“…the US presidential elections [12], the national parliament election in Germany 2009 [13], the general elections in Pakistan 2013 [14] or the presidential election in Brazil 2014 [15]. The methodological approaches of this research differ in the unit of text analyzed, varying from word, sentence, paragraph [15], to a semantic unit such as aspect [16], opinion [17], topic [18], or political issue [19].…”

Section: Sentiment Analysismentioning

confidence: 99%

“…The empirical study used Amazon Mturk to acquire a sample of 1279 participants in the last week (13)(14)(15)(16)(17)(18)(19) May 2019) before the last Game of Thrones episode aired on television. For the data collection, an online questionnaire was answered by 1279 participants.…”

Section: A Participantsmentioning

confidence: 99%

See 2 more Smart Citations

Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

2020

2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

View full text Add to dashboard Cite

This paper analyzes how candidate choice prediction improves by different psychological predictors. To investigate this question, it collected an original survey dataset featuring the popular TV series "Game of Thrones". The respondents answered which character they anticipated to win in the final episode of the series, and explained their choice of the final candidate in free text from which sentiments were extracted. These sentiments were compared to feature sets derived from candidate likeability and candidate personality ratings. In our benchmarking of 10-fold cross-validation in 100 repetitions, all feature sets except the likeability ratings yielded a 10-11% improvement in accuracy on the holdout set over the base model. Treating the class imbalance with synthetic minority oversampling (SMOTE) increased holdout set performance by 20-34% but surprisingly not testing set performance. Taken together, our study provides a quantified estimation of the additional predictive value of psychological predictors. Likeability ratings were clearly outperformed by the feature sets based on personality, emotional valence, and basic emotions.

show abstract

“…Participants 16.1% as moderately high, 6.4% as somewhat high, 2.34% as not high and 0.6% as not high at all.…”

Section: B Descriptive Statisticsmentioning

confidence: 93%

Section: Sentiment Analysismentioning

confidence: 99%

See 1 more Smart Citation

Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice

2020

2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

View full text Add to dashboard Cite

show abstract

“…After determining the aspects to be reviewed, the next step is to classify the customer reviews into predetermined aspects. Some keywords that often appear in hotel review texts on every aspects is defined by [7] combined with data from [18] has follows: Table 2. Pre-processing process…”

Section: Keyword Term List For Hotel Aspectmentioning

confidence: 99%

“…The survey conducted by [6] revealed that almost 95% of tourists made booking decisions by first reading hotel reviews online, and many tourists make online hotel reviews as one of the most important factors in their decision to choose a hotel. Online ratings and customer reviews can be used to help customers make decisions but the reviews give better insight into the hotel [7].…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Hotel Reviews Using Latent Dirichlet Allocation, Semantic Similarity and LSTM

Priyantina¹,

Sarno²

2019

IJIES

View full text Add to dashboard Cite

Product reviews are usually determined by sentiment of customers; however sentiment analysis based on aspects still need further research. A hotel commonly has five aspects, which are location, meal, service, comfort and cleanliness. This research proposes methods to determine review sentiment according to the hotel aspects. A hotel reviews are preprocessed into a term list. Firstly, Latent Dirichelet Allocation (LDA) determines the hidden topics of a term list; then Semantic Similarity categorizes the term list based on the topic resulted by Latent Dirichelet Allocation (LDA) into the five aspects of a hotel. Then in calculating similarity measurement, the term list is expanded by using the Term Frequency-Inverse Cluster Frequency (TF-ICF) method. Finally, a classification of customer sentiment (satisfied or dissatisfied) is conducted by using the combination of Word Embedding and Long-short Term Memory (LSTM). The results show that the proposed method can classify the reviews into the five hotel aspects. The highest aspect categorization performance is obtained by using LDA + TF-ICF 100% + Semantic Similarity which reaches 85%; the performance sentiment classification for the highest aspect-based sentiment analysis is obtained by using Word Embedding + LSTM which reaches 93%; and the comfort aspect receives more negative sentiments compared to the sentiments of other aspects. Also the results show that a sentiment is influenced by an aspect.

show abstract