A Comparative Analysis of Clustering Quality Based on Internal Validation Indices for Dimensionally Reduced Social Media Data

Renjith, Shini; Sreekumar, A.; Jathavedan, M.

doi:10.1007/978-981-15-3514-7_78

Cited by 3 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The amount of data makes it difficult for users to access priority events based on features stored on their social networking profiles. To overcome this limit, various event recommendation systems have been developed [15]. However, these systems use a limited number of event dimensions and user capabilities.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Enabled Social Media Recommendation Based on User Comments

Saraswathi¹,

Mohanraj²,

Suresh³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Nowadays, review systems have been developed with social media Recommendation systems (RS). Although research on RS social media is increasing year by year, the comprehensive literature review and classification of this RS research is limited and needs to be improved. The previous method did not find any user reviews within a time, so it gets poor accuracy and doesn't filter the irrelevant comments efficiently. The Recursive Neural Network-based Trust Recommender System (RNN-TRS) is proposed to overcome this method's problem. So it is efficient to analyse the trust comment and remove the irrelevant sentence appropriately. The first step is to collect the data based on the transactional reviews of social media. The second step is pre-processing using Imbalanced Collaborative Filtering (ICF) to remove the null values from the dataset. Extract the features from the pre-processing step using the Maximum Support Grade Scale (MSGS) to extract the maximum number of scaling features in the dataset and grade the weights (length, count, etc.). In the Extracting features for Training and testing method before that in the feature weights evaluating the softmax activation function for calculating the average weights of the features. Finally, In the classification method, the Recursive Neural Network-based Trust Recommender System (RNN-TRS) for User reviews based on the Positive and negative scores is analysed by the system. The simulation results improve the predicting accuracy and reduce time complexity better than previous methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning Enabled Social Media Recommendation Based on User Comments

Saraswathi¹,

Mohanraj²,

Suresh³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…The Davies-Bouldin (DB) index 12 is used to evaluate cluster quality that is well separated and compact and is evaluated by taking the ratio of inter-cluster to intra-cluster distances. As per the definition of these indices, 13,14 better clustering quality is assumed when comparably high scores are reported for Silhouette and Calinski-Harabasz indices and comparably low scores are reported for Davies-Bouldin index.…”

Section: Clustering Qualitymentioning

confidence: 99%

“…We could also find a few empirical studies comparing the quality and performance of clustering algorithms as in References 40–46. There are a few studies that cover experimental analysis on the impact of dimensionality reduction on clustering process 13,14 …”

Section: Related Workmentioning

confidence: 99%

Taxonomy grooming algorithm ‐ An autodidactic domain specific dimensionality reduction approach for fast clustering of social media text data

Renjith

Sreekumar

Jathavedan

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Social media being the most eminent source toward the growth of big data is important for information retrieval‐based applications to improve the efficiency in proportional to the volume it must deal with. One way to achieve better performance is to upgrade the processing capacity and the alternative option is to improve the processing methodology. The latter can be achieved using smarter processing techniques and/or better algorithms. Reducing the data volume that needs to be processed is a good strategy and it can be achieved by extracting only the relevant information via user segmentation by adopting an appropriate clustering technique. However, while dealing with text content, clustering algorithms do suffer due to the very high dimensions to be dealt with. Since the domain‐specific aspects are getting lost while applying traditional dimensionality reduction approaches, it is important to device an alternate strategy. This work proposes a taxonomy grooming algorithm (TGA), an autodidactic domain‐specific dimensionality reduction approach, for fast clustering of social media text data. Our experiment results are very promising and the dimensionality reduction using TGA resulted in better results in comparison with the traditional dimensionality reduction approaches.

show abstract