• SAYALI JOAG
• MRS. RUPALI DALVI

Online social networks have produced bunch of online social groups where individuals can collaborate and exchange their ideas. The real problems that conflicts with the user security and convenience are confidentiality break, groups without inception, confusion created from various groups’ difficulty in managing groups. This can be overcome to an extent by an automated filtering method required to categorizing group members based on their responses. This paper proposes clustering of group posts on thematic, emotional, stylistic, sentimental and psycholinguistic methods and group members are categorized based on their responses to the posts belonging to different clustering methods. This categorization helps to stop irrelevant notifications to the users which are received from more than one groups, via recommending the posts which might interest the users. It also helps to identify the group members those violate group policies by posting negative posts. The post categorization increases the performance where there are large numbers of members in a social group by performing linguistic clustering. The contribution work is to implement location-aware personalized posts recommendation using user’s behavioral patterns and their geographic location. Another, important work is to implement text-to-speech system converting English text into speech using speech synthesis technique. The system gives user rating to the users who share posts depending on the cluster they belong to. The system provides read later post functionality to the users. The system also provides the users with hash-tag recommendations. The system also provides user with posts based on long - term and short - term analysis. The system has been tested on Twitter API group data where a significant solution to an unaddressed problem associated with social networking groups is offered.

Sentiment Analysis , Emotion Analysis, Multi-level Clustering, Psycholinguistics, LDA, Text to speech ,Stylistics Clustering, NLP, Vector Computation

"A Survey on Linguistic-Based and User-Based Recommending Posts Using Two-Level Clustering Methods", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 9, page no.530-536, September-2019, Available :http://www.jetir.org/papers/JETIR1912068.pdf

"A Survey on Linguistic-Based and User-Based Recommending Posts Using Two-Level Clustering Methods", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 9, page no. pp530-536, September-2019, Available at : http://www.jetir.org/papers/JETIR1912068.pdf