Learning similarity with cosine similarity ensemble

Xia, Peipei; Zhang, Li; Li, Fanzhang

doi:10.1016/j.ins.2015.02.024

Cited by 290 publications

(127 citation statements)

References 21 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…There are many ways to calculate semantic similarity, one of them using cosine similarity. Cosine similarity works by measuring the angle between two vectors [24]. The cosine similarity equation can be seen in Eq.…”

Section: Semantic Similaritymentioning

confidence: 99%

Aspect Based Sentiment Analysis for Restaurant Reviews Using Hybrid ELMoWikipedia and Hybrid Expanded Opinion Lexicon-SentiCircle

Nurifan¹,

Sarno²,

Sungkono³

2019

IJIES

View full text Add to dashboard Cite

Many restaurant review analysis have been done, however only few analysis have been done for specific aspects of a restaurant. In this context this paper proposes aspect based restaurant analysis which includes Physical environment, Food quality, Service quality and Price fairness. The analysis steps include Aspect Term Extraction (ATE), Aspect Keyword Extraction (AKE), Aspect Categorization (AC) and Sentiment Analysis (SA). ATE employs the modification of Double Propagation method and several Topic Modelling methods, AKE utilizes Term Frequency-Inverse Cluster Frequency (TF-ICF), in AC we propose Hybrid ELMo-Wikipedia (HEW), and in SA we propose Hybrid Expanded Opinion Lexicon-SentiCircle (HEOLS). The results show that our modification of the methods used in ATE could increase the f1measure of the AC by average 2%, then the HEW that we proposed had better f1measure compared to other similar methods by average 6%. Other than that, our proposed HEOLS can expand and redetermine the Opinion Lexicon polarity and can increase f1measure of SA by 6%.

show abstract

Section: Semantic Similaritymentioning

confidence: 99%

Aspect Based Sentiment Analysis for Restaurant Reviews Using Hybrid ELMoWikipedia and Hybrid Expanded Opinion Lexicon-SentiCircle

Nurifan¹,

Sarno²,

Sungkono³

2019

IJIES

View full text Add to dashboard Cite

show abstract

“…Lack of motivation to read the content of the privacy policy each time may be due to the feeling that the information is reproduced. The study of text similarity was carried out using the cosine of vector similarity method (Xia et al, 2015) and indicated an average value of similarity between individual texts to be 75.5 percent. The smallest value was noted between the privacy policy of Doz.pl and Congee.pl, which is contained at the end of the website's regulations.…”

Section: User Data and Their Protectionmentioning

confidence: 99%

Managing Data in Digital Marketing

Szymkowiak¹

2019

View full text Add to dashboard Cite

In Chapter 3, a discussion was undertaken about the merits of distinguishing data science as an area of science and the perception of data science due to the progress of computational possibilities. The historical outline of data science was discussed, along with a reference to the data-driven approach. An additional problem raised in this chapter relates to determining the role of the scientist in the process of knowledge discovery. Moreover, in the context of the development of the tooling and methodological apparatus based on analytical autonomous operation. Various areas of data science were characterized, and traditional and modern methods were compared in the process of knowledge discovery, also showing the relationship between individual elements based on the knowledge pyramid. In addition, areas of marketing where data mining

show abstract

“…The triangle inequality does not hold for the cosine dissimilarity. Text documents are often clustered using the cosine dissimilarity function [41] .…”

Section: Non-metric Dissimilaritiesmentioning

confidence: 99%