Theme Based Clustering of Tweets

Tripathy, Rudra M.; Sharma, Shashank; Joshi, Sachindra; Mehta, Sameep; Bagchi, Amitabha

doi:10.1145/2567688.2567694

Cited by 7 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After pre-processing of tweets, their clustering is the major area of concern. Initially, k-means algorithm have been proposed and used for clustering tweets (Kaleel and Abhari, 2015;Tripathy et al, 2014). But, this was convex cluster-based algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…Also, different categorization approaches for sentiment analysis were compared (Bravo-Marquez et al, 2014). On the other side, theme-based clustering of tweets was examined by using Wikipedia resource (Tripathy et al, 2014).…”

Section: Event Detectionmentioning

confidence: 99%

“…Cosine similarity is used to measure the extent of similarity among different tweets. This is used in clustering of tweets using Wikipedia and other distance measure techniques (Tripathy et al, 2014). Precision and recall are measured on the basis of true positive, true negative, false negative or false positive.…”

Section: Data Representationmentioning

confidence: 99%

See 2 more Smart Citations

Review on event detection techniques in social multimedia

Garg

Kumar

2016

Online Information Review

View full text Add to dashboard Cite

Purpose – Social Media is one of the largest platforms to voluntarily communicate thoughts. With increase in multimedia data on social networking websites, information about human behaviour is increasing. This user-generated data are present on the internet in different modalities including text, images, audio, video, gesture, etc. The purpose of this paper is to consider multiple variables for event detection and analysis including weather data, temporal data, geo-location data, traffic data, weekday’s data, etc. Design/methodology/approach – In this paper, evolution of different approaches have been studied and explored for multivariate event analysis of uncertain social media data. Findings – Based on burst of outbreak information from social media including natural disasters, contagious disease spread, etc. can be controlled. This can be path breaking input for instant emergency management resources. This has received much attention from academic researchers and practitioners to study the latent patterns for event detection from social media signals. Originality/value – This paper provides useful insights into existing methodologies and recommendations for future attempts in this area of research. An overview of architecture of event analysis and statistical approaches are used to determine the events in social media which need attention.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Event Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Review on event detection techniques in social multimedia

Garg

Kumar

2016

Online Information Review

View full text Add to dashboard Cite

show abstract

“…Theme recognition has been extensively studied in various fields, including music analysis and music information retrieval, 49 , 50 natural language processing and text analysis, 51 , 52 and computer vision and image understanding. In the domain of image understanding, theme recognition has been utilized to guide various computer vision tasks, such as painting scene recognition, 53 multi-class object recognition and segmentation, 54 and image caption generation 55 , 56 .…”

Section: Related Workmentioning

confidence: 99%

TEG: image theme recognition using text-embedding-guided few-shot adaptation

Wang,

Lu,

Wang

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Grouping images into different themes is a challenging task in photo book curation. Unlike image object recognition, image theme recognition focuses on the understanding of the main subject or overall meaning conveyed by an image. However, it is challenging to achieve satisfactory performance using existing general image recognition methods. In this work, we aim to solve the image theme recognition task with few-shot training samples using pre-trained contrastive language-image models. A text-prompt-guided few-shot image adaptation framework is proposed, which incorporates a text-embedding-guided classifier and an auxiliary classification loss to exploit embedded visual and text features, stabilize the network training, and enhance recognition performance. We also present an annotated dataset Theme25 for studying image theme recognition. We conducted experiments on our Theme25 dataset as well as the publicly available CIFAR100 and ImageNet datasets to demonstrate the superiority of our method over the compared stateof-the-art methods.

show abstract

“…Tripathy, et al [5] proposed the clustering technique based on word frequency and Wikipedia topic taxonomy to find the discussed topic in the tweet. The research has revealed that the proposed algorithm has given better result than the algorithm which only involve word frequency.…”

Section: Related Workmentioning

confidence: 99%

Clustering on Twitter: case study Twitter account of higher education institution in Indonesia

Hamzah

Hidayatullah

2018

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. Recently, higher education institutions have been using Twitter as one of tools to enhance their communication network. This paper aims to cluster Twitter data retrieved from the official Twitter account of higher education institutions in Indonesia. We expect to obtain a valuable information from the tweet posted. Furthermore, we use Twitter's hashtag as a basis of clustering. We collect data from n=10 institutions that have an official account on Twitter. The Affinity Propagation algorithm was employed to perform the clustering task. According to the clustering results, we conclude that higher education in Indonesia mostly utilize Twitter to post general information, news, agenda, announcement, information to the new students, and achievement.

show abstract

Theme Based Clustering of Tweets

Cited by 7 publications

References 8 publications

Review on event detection techniques in social multimedia

Review on event detection techniques in social multimedia

TEG: image theme recognition using text-embedding-guided few-shot adaptation

Clustering on Twitter: case study Twitter account of higher education institution in Indonesia

Contact Info

Product

Resources

About