Lexicon-Based Text Analysis for Twitter and Quora

Nishant, Potnuru Sai; Mohan, Bhaskaruni Gopesh Krishna; Chandra, Balina Surya; Lokesh, Yangalasetty; Devaraju, Gantakora; Revanth, Madamala

doi:10.1007/978-3-030-38040-3_32

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Social media and other blogging sites such as Quora, Twitter, Yahoo Answers, Facebook, and Answerbag have gained so much popularity that they became a necessity for modern users [1][2][3]. However, Quora evolved into one of the most popular platforms for questioning and answering, with 190 million users and millions of questions being answered in a timeframe of a month [1,2,4]. With a massive number of users and their queries, the user's safety and security should not be compromised, which can be avoided by filtering inappropriate and unrelated questions.…”

Section: Introductionmentioning

confidence: 99%

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

Naveed¹,

Sohail²,

Zain³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Question and answer websites such as Quora, Stack Overflow, Yahoo Answers and Answer Bag are used by professionals. Multiple users post questions on these websites to get the answers from domain specific professionals. These websites are multilingual meaning they are available in many different languages. Current problem for these types of websites is to handle meaningless and irrelevant content. In this paper we have worked on the Quora insincere questions (questions which are based on false assumptions or questions which are trying to make a statement rather than seeking for helpful answers) dataset in order to identify user insincere questions, so that Quora can eliminate those questions from their platform and ultimately improve the communication among users over the platform. Previously, a research was carried out with recurrent neural network and pretrained glove word embeddings, that achieved the F1 score of 0.69. The proposed study has used a pre-trained ULMFiT model. This model has outperformed the previous model with an F1 score of 0.91, which is much higher than the previous studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

Naveed¹,

Sohail²,

Zain³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

Detection and Analysis of Sentiments on Twitter Using Machine Learning Algorithm

Sathyabama¹,

Suganya²,

Nalayini³

et al. 2022

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

Construction of Efficient Smart Voting Machine with Liveness Detection Module

Hamdan¹,

Sathesh²

2021

JIIP

View full text Add to dashboard Cite

Voting is now governed by regulations that specify how a person's choices may be communicated and their desires can be realized. This study proposes an electronic voting machine (EVM) as an alternative for traditional voting methods, which may include the manual utilization of only microcontroller-based circuits. With the identified fingerprint liveness, the proposed technique will make voting considerably easier, more effective, and less likely to result in fraud. The suggested model will support and advance the trustworthiness of all votes and it will also assist in streamlining the counting and verification process. It is difficult to demonstrate that an advanced voting system has been properly designed since several critical criteria must be satisfied. Poll results should be kept private in the database in order to preserve the data. The voting process must also show the votes obtained by the respective candidates. The proposed authenticated voting machine can be applied to the local area elections in order to speed up the process and make the election process more transparent. To maintain its theoretical strength, the proposed research idea needs further study. The model employs radio frequency and fingerprint recognition to maintain the protection.

show abstract

Lexicon-Based Text Analysis for Twitter and Quora

Cited by 3 publications

References 8 publications

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

Detection and Analysis of Sentiments on Twitter Using Machine Learning Algorithm

Construction of Efficient Smart Voting Machine with Liveness Detection Module

Contact Info

Product

Resources

About