The utilization of customer-produced data collected by society broadcasting to scrutinize public estimation and systematic interaction on hire and protection issues is an emerging trend in technical study. This analysis of the data, as well as the introduction of a social question-and-answer website, is part of a larger package aimed at determining the elements that impact community preferences for technological knowledge and thoughts. This study measured the effect of the response stylistic and supporting functions on the number of appointments received with the response using a web search engine, subject modelling, and degeneration data modelling. The results of the model reveal that Quora users are more inclined to talk just about technology when compared to earlier studies based on open evaluations. It may possibly fail if the query's keywords do not match the text content of huge texts including pertinent queries on or after previous techniques, such as CNNMF and NMF, as well as some constraints. Furthermore, consumers are frequently inexperienced and offer vague requests, resulting in mixed outcomes and issues with existing approaches. To address this issue, we offer a Hadoop model for finding topics for short texts that is distributed using semantics and non-negative matrix factorization (HDiSANNMF). It efficiently combines the semantic associations of the word context obsessed by the model, which studies the semantic relationships between words and their context without ignoring the corpus's grammatical shape. The researchers are attempting to rearrange the major findings and propose new ways for modelling distributed themes in order to deal with increasingly complex technologies and platforms, as well as the amount of time and space required to build the model. This portion gives a short-term overview of the structure of public queries and replies from around the world, as well as real-time tracking of the primary issues of accommodation and work opportunities for next-generation technology.