Recognising personality traits using social media

Varshney, Vanshika; Varshney, Aman; Ahmad, Tameem; Khan, Asad

doi:10.1109/icpcsi.2017.8392248

Cited by 16 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reviews that we crawled had a lot of diversity. [13] [15]Extracting features was itself a tough task, as our approach was to define a grammar which failed in various cases of typing errors.After the features were extracted, sentiment analysis was carried out and clusters were made according to the polarity scores. Lastly, the summary that we presented provided the user a feature wise unbiased extraction based summary of the reviews.…”

Section: Discussionmentioning

confidence: 99%

Extractive Research on Summarization Framework for Extracted Features

Bansal¹,

Somya²,

Kamaal³

et al. 2019

IJITEE

Self Cite

View full text Add to dashboard Cite

In the information age, the growth of e-commerce has brought the products’ sale and purchase online and many of the customers prefer to buy it online. To support this preference the users’ reviews of the products plays an important role. So, online merchants wish to take the reviews; experiences of the user, to enhance their business and revenue. Popular and trending products may attract large number of reviews. Further, many of which could be elongated. Extracting useful information with efficiency and accuracy from these so many reviews, of which there are some very long, is a challenging task. This work is an attempt to summarize the customer reviews on products into more useful and shorter version that can help another users’ decision. Reviews available online are crawled for product, each time after extraction, first identification of features of the product will be done and hence polarity will be detected i.e. either a review is positive review or a negative review. After the calculations, summarization of all the features of the product will be generated.

show abstract

Section: Discussionmentioning

confidence: 99%

Extractive Research on Summarization Framework for Extracted Features

Bansal¹,

Somya²,

Kamaal³

et al. 2019

IJITEE

Self Cite

View full text Add to dashboard Cite

show abstract

“…A person's personality can influence life, career, and romance prospects. For companies, knowing a person's personality can be used for employee recruitment, career counseling, and health advice [4]. Several personality models can predict user personality, such as the Mayers-Briggs Type Indicator (MBTI), Big Five Personality, or Dominance Influence Steadiness Conscientiousness (DISC).…”

Section: Introductionmentioning

confidence: 99%

Optimization Prediction of Big Five Personality in Twitter Users

Safitri

Setiawan

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Various kinds of information can be acquired from social media platforms; one of them is on Twitter. User biographical information and tweets are the essential assets for research that can describe the Big Five Personality, including openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several previous studies have tried the prediction of Big Five Personality. However, the authors found problems in how to optimize the work of the personality prediction system. So, in this study, Big Five Personality predictions were carried out on users of Twitter and improved the performance of the personality prediction system. We implement optimization techniques such as sampling, feature selection, and hyperparameter tuning to enhance the performance. This study also applies linguistic feature extraction, such as LIWC and TF-IDF. By using 287 Twitter users that have permitted their data to be crawled acquired from an online survey using Big Five Inventory (BFI), and applying all optimization techniques, the average accuracy result is 84.22% which is a 74.44% gain over the specified baseline.

show abstract