ExMrec2vec: Explainable Movie Recommender System based on Word2vec

Samih, Amina; Ghadi, Abderrahim; Fennan, Abdelhadi

doi:10.14569/ijacsa.2021.0120876

Cited by 14 publications

(5 citation statements)

References 15 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. 𝑤 𝑛 >) is the word embedding for word xi, which might be learned using the traditional Word2Vec technique [9], [30], [31].…”

Section: Sentiment2vecmentioning

confidence: 99%

“…The algorithm shows that Sentiment2Vec taken sentiment as input and returned vectors of words of the sentiment by using Word2Vec [21]. So, in the second step, each word vector of the input sentiment is extracted from Word2Vec [31], then the mean of vectors of words is calculated. In the third step, sentiment scores of each word are extracted from lexicon-based polarity (negative or positive).and we will normalize them.…”

Section: Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced sentiment analysis based on improved word embeddings and XGboost

Samih

Ghadi

Fennan

2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Sentiment analysis is a well-known and rapidly expanding study topic in natural language processing (NLP) and text classification. This approach has evolved into a critical component of many applications, including politics, business, advertising, and marketing. Most current research focuses on obtaining sentiment features through lexical and syntactic analysis. Word embeddings explicitly express these characteristics. This article proposes a novel method, improved words vector for sentiments analysis (IWVS), using XGboost to improve the F1-score of sentiment classification. The proposed method constructed sentiment vectors by averaging the word embeddings (Sentiment2Vec). We also investigated the Polarized lexicon for classifying positive and negative sentiments. The sentiment vectors formed a feature space to which the examined sentiment text was mapped to. Those features were input into the chosen classifier (XGboost). We compared the F1-score of sentiment classification using our method via different machine learning models and sentiment datasets. We compare the quality of our proposition to that of baseline models, term frequency-inverse document frequency (TF-IDF) and Doc2vec, and the results show that IWVS performs better on the F1-measure for sentiment classification. At the same time, XGBoost with IWVS features was the best model in our evaluation.</span>

show abstract

“…. 𝑤 𝑛 >) is the word embedding for word xi, which might be learned using the traditional Word2Vec technique [9], [30], [31].…”

Section: Sentiment2vecmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

Enhanced sentiment analysis based on improved word embeddings and XGboost

Samih

Ghadi

Fennan

2023

IJECE

View full text Add to dashboard Cite

show abstract

“…Each layer contains at least one processing unit. Each layer of output is a representation of the data, and the level of representation increases as the processing level increases (Shambour, 2021). DL is another important Artificial Intelligence (AI) method in the era of big data.…”

Section: B Construction Of An Employment Recommendation System Based ...mentioning

confidence: 99%

“…The problems graduates face in employment are the personal unsuitability of information and information overload. It is of practical significance for the recommendation system to be applied to the employment of graduates, which can recommend a personalized collection of enterprises for graduates to reduce their employment pressure and improve employment rate and employment satisfaction (SAMIH, GHADI & FENNAN, 2021). The architecture of DL can implement end-to-end derivability of the overall model, which is conducive to integrating multiple network structures.…”

Section: B Construction Of An Employment Recommendation System Based ...mentioning

confidence: 99%

The Employment Management for College Students Based on Deep Learning and Big Data

Shi

2023

IEEE Access

View full text Add to dashboard Cite

College graduates face increasing employment pressure due to the continuous expansion of colleges and universities' enrollment scales. It highlights the shortcomings of college students' employability, and these deficiencies can be improved and enhanced through the role of ideological and political education. Firstly, this paper summarizes the current situation of college students' employment management at this stage and finds countermeasures to improve their employability to help them correctly understand their employment situation. Secondly, the reasons for the lack of ideological and political education in cultivating college students' employability are emphasized to clarify the relationship between ideological and political education and college students' employment management. Besides, specific suggestions are put forward on the issue of cultivating college students' employability. Finally, the deep learning (DL) recommendation model is used to effectively connect the correlation between student data and enterprise information to improve the employment rate and employment satisfaction of colleges and universities, and the two are jointly trained. The experimental results show that: (1) The proposed model can mine the characteristics of students and enterprises and conduct feature interaction with a good hit rate. (2) The proposed model can interact with the two tasks and mine the relationship information to improve the performance of the recommended task. This paper aims to use DL methods to analyze and construct the portrait of college students' employability needs and study the accurate recommendation system based on the employment matching degree of college students to improve employment management and ideological and political education methods.INDEX TERMS employment of college students; employment management; ideological and political education; deep learning; recommendation system

show abstract

“…Along with BERT, a number of deep learning models were also used in this ABSA work. Word2Vec [28] preprocessing technique was used in those models for feature extraction. Some brief descriptions of the algorithms are given below:…”

Section: E Model Developmentmentioning

confidence: 99%

Aspect-based Sentiment Analysis for Bengali Text using Bidirectional Encoder Representations from Transformers (BERT)

Samia¹,

Rajee²,

Hasan³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Public opinion is important for decision-making on numerous occasions for national growth in democratic countries like Bangladesh, the USA, and India. Sentiment analysis is a technique used to determine the polarity of opinions expressed in a text. The more complex stage of sentiment analysis is known as Aspect-Based Sentiment Analysis (ABSA), where it is possible to ascertain both the actual topics being discussed by the speakers as well as the polarity of each opinion. Nowadays, people leave comments on a variety of websites, including social networking sites, online news sources, and even YouTube video comment sections, on a wide range of topics. ABSA can play a significant role in utilizing these comments for a variety of objectives, including academic, commercial, and socioeconomic development. In English and many other popular European languages, there are many datasets for ABSA, but the Bengali language has very few of them. As a result, ABSA research on Bengali is relatively rare. In this paper, we present a Bengali dataset that has been manually annotated with five aspects and their corresponding sentiment. A baseline evaluation was also carried out using the Bidirectional Encoder Representations from Transformers (BERT) model, with 97% aspect detection accuracy and 77% sentiment classification accuracy. For aspect detection, the F1-score was 0.97 and for sentiment classification, it was 0.77.

show abstract

ExMrec2vec: Explainable Movie Recommender System based on Word2vec

Cited by 14 publications

References 15 publications

Enhanced sentiment analysis based on improved word embeddings and XGboost

Enhanced sentiment analysis based on improved word embeddings and XGboost

The Employment Management for College Students Based on Deep Learning and Big Data

Aspect-based Sentiment Analysis for Bengali Text using Bidirectional Encoder Representations from Transformers (BERT)

Contact Info

Product

Resources

About