Deep Learning for Hot Topic Extraction from Social Streams

Rekik, Amal; Jamoussi, Salma

doi:10.1007/978-3-319-52941-7_19

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…29,30 Deep learning algorithms have recently been used for dimension reduction in clustering text data. For example, in a research study, the authors presented stacked autoencoder (SAE)-Clus, 31 a method based on the deep learning SAEs. They applied the proposed approach to reduce the data dimension over feature vectors obtained from a bag-of-words model.…”

Section: Related Researchmentioning

confidence: 99%

Deep embedding for mental health content on social media using vector space model with feature clusters

Gupta

Katarya

2022

Concurrency and Computation

View full text Add to dashboard Cite

Over the years, various document-clustering techniques were developed to group the textual data. The performance of document clustering systems heavily relies on the optimal use of text representations. Vector space model is an extensively used technique by existing clustering algorithms to present the text in a structured form.However, such representations suffer from a lack of semantic associations, high dimensionality, and sparsity. In order to enrich the document representation by retaining the semantic and morphological associations, this paper introduced a word cluster-based modified term frequency-inverse document frequency (WC_MTI) model, in which semantically associated word embeddings from the word2vec are supplemented with morphological information using kernel principal component analysis. In addition, to address high dimensionality and sparsity issues and improve the clustering, we use a self-training technique that learns discriminative features using the WC_MTI model and autoencoder (AE) and then updates the encoder network weights using assignments from a clustering algorithm as supervision. The proposed model organizes documents into topically compatible clusters by maintaining the semantic and morphological similarity between terms using the skip-gram with negative sampling (SGNS) and low-dimensional vector representations. We evaluate the proposed approach against the existing text representation methods. Experimental findings suggest that the proposed approach enhanced the average accuracy by 89.62%.

show abstract

Section: Related Researchmentioning

confidence: 99%

Deep embedding for mental health content on social media using vector space model with feature clusters

Gupta

Katarya

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Deep autoencoders are very powerful in terms of reducing the dimension and outperform Principal Component Analysis (PCA) in image compression (Côté & Larochelle, 2016). Deep autoencoders were used in topics detection (Bougteb et al, 2019;Rekik & Jamoussi, 2016) as well as in recommender systems (Strub et al, 2016;Kuchaiev et al, 2017;Sedhain et al, 2015). In (Wang & Wang, 2014), authors used the Hierarchical linear model with Deep Belief Network (HLDBN) based on a probabilistic graphical model and Deep Belief Network (DBN).…”

Section: Related Workmentioning

confidence: 99%

A Deep Autoencoder-Based Hybrid Recommender System

Bougteb

Ouhbi

Frikh³

et al. 2022

International Journal of Mobile Computing and Multimedia Communications

View full text Add to dashboard Cite

Recommender systems build their suggestions on rating data, given explicitly or implicitly by users on items. These ratings create a huge sparse user-item rating matrix which opens two challenges for researchers on the field. The first challenge is the sparsity of the rating matrix and the second one is the scalability of the data. This article proposes a hybrid recommender system based on deep autoencoder to learn the user interests and reconstruct the missing ratings. Then, SVD++ decomposition is employed, in parallel, to hold information of correlation between different features factors. Additionally, the authors gave a deep analysis of the top-N recommender list from the user's perspective to ensure that the proposed model can be used for practical application. Experiments showed that the proposed model performed better with high-dimensional datasets, and outperformed various hybrid algorithms in terms of RMSE, MAE, and in terms of the final top-N recommendation list.

show abstract

“…As for the conventional classification, deep learning usually requires a significant amount of labelled data for each class to train networks in a fully-supervised manner. However, regarding applications such as topic extraction [1] and event detection [2], some classes are less common in the real world, making it difficult to collect sufficient samples for model training. Besides, with the widespread popularity of social media, a large number of emerging topics or events are constantly being introduced.…”

Section: Introductionmentioning

confidence: 99%

Generalised Zero-shot Learning for Entailment-based Text Classification with External Knowledge

Wang

Chen

et al. 2022

2022 IEEE International Conference on Smart Computing (SMARTCOMP)

View full text Add to dashboard Cite

Text classification techniques have been substantially important to many smart computing applications, e.g. topic extraction and event detection. However, classification is always challenging when only insufficient amount of labelled data for model training is available. To mitigate this issue, zero-shot learning (ZSL) has been introduced for models to recognise new classes that have not been observed during the training stage. We propose an entailment-based zero-shot text classification model, named as S-BERT-CAM, to better capture the relationship between the premise and hypothesis in the BERT embedding space. Two widely used textual datasets are utilised to conduct the experiments. We fine-tune our model using 50% of the labels for each dataset and evaluate it on the label space containing all labels (including both seen and unseen labels). The experimental results demonstrate that our model is more robust to the generalised ZSL and significantly improves the overall performance against baselines.

show abstract

Deep Learning for Hot Topic Extraction from Social Streams

Cited by 7 publications

References 10 publications

Deep embedding for mental health content on social media using vector space model with feature clusters

Deep embedding for mental health content on social media using vector space model with feature clusters

A Deep Autoencoder-Based Hybrid Recommender System

Generalised Zero-shot Learning for Entailment-based Text Classification with External Knowledge

Contact Info

Product

Resources

About