Enhance sentiment analysis on social networks with social influence analytics

Chouchani, Nadia; Abed, Mourad

doi:10.1007/s12652-019-01234-0

Cited by 19 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Be that as it may, given customer score information, relational association examination can overhaul feeling mining. [5] Notion assessment obligates remained overseen by way of a Natural Language Processing mission on different degrees of granularity. Beginning after existence a record equal representation mission, it has been administered at the sentence near also fundamentally additionally beginning late at the enunciation level.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis on Social Network

2021

IJATCSE

View full text Add to dashboard Cite

As the Web quickly advances, Web clients are developing with it. In a time of social connectedness, individuals are turning out to be increasingly more excited about associating, sharing, and teaming up through informal communities, online networks, sites, Wikis, and other online communitarian media. Lately, this aggregate insight has spread on various zones, with specific spotlight on fields identified with regular daily existence, for example, business, the travel industry, instruction, and wellbeing, making the size of the Social Web extend exponentially

show abstract

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis on Social Network

2021

IJATCSE

View full text Add to dashboard Cite

show abstract

“…In order to improve the accuracy of recommendation, emotion analysis is combined with other factors. Chouchani et al [18] used information about social influence processes to improve emotion analysis. Phan et al [19] proposed a new approach based on a feature ensemble model related to tweets containing fuzzy emotion by taking into account elements such as lexical, word-type, semantic, position, and emotion polarity of words.…”

Section: Recommendation Algorithms Based On Content Descriptionmentioning

confidence: 99%

“…At present, the research of deep learning technology of integrating multi-source heterogeneous data, fusion scoring matrix and review text, and multi-featured collaborative recommendation has become a hot topic [17] [18][19][20]. Based on the above research, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion (DMHR algorithm), which aims at the balance of user score distribution and the difficulty of multi-recommendation in recommendation system.…”

Section: Introductionmentioning

confidence: 99%

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

et al. 2020

View full text Add to dashboard Cite

The recommendation system is an effective means to solve the information overload problem that exists in social networks, which is also one of the most common applications of big data technology. Thus, the matrix decomposition recommendation model based on scoring data has been extensively studied and applied in recent years, but the data sparsity problem affects the recommendation quality of the model. To this end, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion which makes a personalized recommendation with user-post interaction ratings, implicit feedback and auxiliary information in a hybrid recommendation system. Specifically, the HITS algorithm is used to process the data set, which can filter out the users and posts with high influence and eliminate most of the low-quality users and posts. Secondly, the calculation method of measuring the similarity of candidate posts and the method of calculating K nearest neighbors are designed, which solves the problem that the text description information of post content in the recommendation system is difficult to mine and utilize. Then, the cooperative training strategy is used to achieve the fusion of two recommended views, which eliminates the data distribution deviation added to the training data pool in the iterative training. Finally, the performance of the DMHR algorithm proposed in this paper is compared with other state-of-art algorithms based on the Twitter dataset. The experimental results show that the DMHR algorithm has significant improvements in score prediction and recommendation performance.

show abstract

“…-Le degré entrant : c'est le nombre des abonnés d'un utilisateur reflétant sa popularité. Afin de calculer les mesures d'influence entre deux utilisateurs,étant donné leurs données sociales, nous avons recours au modèle d'influence représenté par un graphe hétérogène normalisé d'influence (Chouchani, Abed, 2019). Ce graphe, comme le montre la figure 4 copmrend les magnitudes d'influence des acteurs dans leurs réseauxégocentriques ainsi que les mesures d'influence entre eux définies par : Méthode SVM Cette méthode est utilisée dans divers problèmes de classification en cherchant un hyperplan qui distingue deux classes tout en respectant une contrainte qui stipule que la marge entre les classes doitêtre maximisée.…”

Section: Algorithm 2 En Is(unclassified

“…Nous visonsà apprendre ces paramètres en maximisant logP (Y ) en fonction des paramètres μ k,l et λ k,l . Pour ce faire, nous utilisons le modèle d'Analyse des Sentiments au niveau utilisateur basé sur les phénomènes d'influence et d'homophilie (Chouchani, Abed, 2019).…”

Section: Détails De L'étape 3 : Divisionunclassified