| 1. |
- Hammar, Kim, et al.
(författare)
-
Deep text classification of Instagram data using word embeddings and weak supervision
- 2020
-
Ingår i: WEB INTELLIGENCE. - : IOS PRESS. - 2405-6456. ; 18:1, s. 53-67
-
Tidskriftsartikel (refereegranskat)abstract
- With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on training data annotated manually by humans, which in practice is both difficult and expensive to obtain. In this paper, we present methods for weakly supervised text classification of Instagram text. We analyze a corpora of Instagram posts from the fashion domain and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we demonstrate that in absence of annotated training data, using weak supervision to train models is a viable approach. With weak supervision we were able to label a large dataset in hours, something that would have taken months to do with human annotators. Using the dataset labeled with weak supervision in combination with generative modeling, an F-1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance.
|
|
| 2. |
- Hammar, Kim, et al.
(författare)
-
Deep Text Mining of Instagram Data Without Strong Supervision
- 2018
-
Ingår i: Proceedings - 2018 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2018. - : IEEE. - 9781538673256 ; , s. 158-165
-
Konferensbidrag (refereegranskat)abstract
- With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. This textual data can be analyzed for the purpose of improving user recommendations and detecting trends. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on annotated training data, which in practice is both difficult and expensive to obtain. In this paper, we present methods for unsupervised mining of fashion attributes from Instagram text, which can enable a new kind of user recommendation in the fashion domain. In this context, we analyze a corpora of Instagram posts from the fashion domain, introduce a system for extracting fashion attributes from Instagram, and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we confirm that word embeddings are a useful asset for information extraction. Experimental results show that information extraction using word embeddings outperforms a baseline that uses Levenshtein distance. The results also show the benefit of combining weak supervision signals using generative models instead of majority voting. Using weak supervision and generative modeling, an F1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance. Finally, our empirical study provides one of the few available studies on Instagram text and shows that the text is noisy, that the text distribution exhibits the long-tail phenomenon, and that comment sections on Instagram are multi-lingual.
|
|
| 3. |
- Jaradat, Shatha
(författare)
-
Deep cross-domain fashion recommendation
- 2017
-
Ingår i: RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems. - New York, NY, USA : Association for Computing Machinery (ACM). - 9781450346528 ; , s. 407-410
-
Konferensbidrag (refereegranskat)abstract
- With the increasing number of online shopping services, the number of users and the quantity of visual and textual information on the Internet, there is a pressing need for intelligent recommendation systems that analyze the user's behavior amongst multiple domains and help them to find the desirable information without the burden of search. However, there is little research that has been done on complex recommendation scenarios that involve knowledge transfer across multiple domains. This problem is especially challenging when the involved data sources are complex in terms of the limitations on the quantity and quality of data that can be crawled. The goal of this paper is studying the connection between visual and textual inputs for better analysis of a certain domain, and to examine the possibility of knowledge transfer from complex domains for the purpose of efficient recommendations. The methods employed to achieve this study include both design of architecture and algorithms using deep learning technologies to analyze the effect of deep pixel-wise semantic segmentation and text integration on the quality of recommendations. We plan to develop a practical testing environment in a fashion domain.
|
|
| 4. |
- Jaradat, Shatha, et al.
(författare)
-
Dynamic CNN Models For Fashion Recommendation in Instagram
- 2018
-
Ingår i: 2018 IEEE INT CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, UBIQUITOUS COMPUTING & COMMUNICATIONS, BIG DATA & CLOUD COMPUTING, SOCIAL COMPUTING & NETWORKING, SUSTAINABLE COMPUTING & COMMUNICATIONS. - : IEEE COMPUTER SOC. - 9781728111414 ; , s. 1144-1151
-
Konferensbidrag (refereegranskat)abstract
- Instagram as an online photo-sharing and social-networking service is becoming more powerful in enabling fashion brands to ramp up their business growth. Nowadays, a single post by a fashion influencer attracts a wealth of attention and a magnitude of followers who are curious to know more about the brands and style of each clothing item sitting inside the image. To this end, the development of efficient Deep CNN models that can accurately detect styles and brands have become a research challenge. In addition, current techniques need to cope with inherent fashion-related data issues. Namely, clothing details inside a single image only cover a small proportion of the large and hierarchical space of possible brands and clothing item attributes. In order to cope with these challenges, one can argue that neural classifiers should become adapted to large-scale and hierarchical fashion datasets. As a remedy, we propose two novel techniques to incorporate the valuable social media textual content to support the visual classification in a dynamic way. The first method is adaptive neural pruning (DynamicPruning) in which the clothing item category detected from posts' text analysis can be used to activate the possible range of connections of clothing attributes' classifier. The second method (DynamicLayers) is a dynamic framework in which multiple-attributes classification layers exist and a suitable attributes' classifier layer is activated dynamically based upon the mined text from the image. Extensive experiments on a dataset gathered from Instagram and a baseline fashion dataset (DeepFashion) have demonstrated that our approaches can improve the accuracy by about 20% when compared to base architectures. It is worth highlighting that with Dynamiclayers we have gained 35% accuracy for the task of multi-class multi-labeled classification compared to the other model.
|
|
| 5. |
- Jaradat, Shatha, et al.
(författare)
-
Fashion Recommender Systems
- 2022. - 3rd
-
Ingår i: Recommender Systems Handbook. - New York, NY : Springer Nature. ; , s. 1015-1055
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- The increasing popularity of online fashion and online retail platforms is having a visible impact on the shopping experience of billions of customers, making millions of products available in online catalogs thus eliminating the need for physical visits to various stores and for waiting in long queues or trying on clothes in dressing rooms by providing personalized and affordable deliveries. This in turn has created novel challenges for platform providers, within which proper understanding of fashion choices of shoppers plays a crucial role. Shoppers tend to feel overwhelmed by the sheer choice of the assortment and brands, not being able to receive effective suggestions matching their style preferences as well as not being able to spot the right size and fit during the shopping experience. As a result, recommender systems are gaining momentum by mining through large and diverse silos of product catalogs as well as customer datasets in order to provide personalized recommendations of outfits, complimenting the shopping session with similar and relevant products, understanding and suggesting the correct size and fit for shoppers, recommending with personalized styles and leveraging the social influence affecting the choice of style and buying behavior of new generations of shoppers. To this end, within this chapter we aim to present a state of the art view of the advancements within the field of recommendation systems in the domain of fashion. We discuss in detail the open challenges and provide an outlook on current and future work in this exciting multidisciplinary field.
|
|
| 6. |
- Jaradat, Shatha, et al.
(författare)
-
Learning What to Share in Online Social Networks Using Deep Reinforcement Learning
- 2018
-
Ingår i: Machine Learning Techniques for Online Social Networks. - Cham : Springer International Publishing. ; , s. 115-133
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- Online networking sites tried their best to have right privacy mechanisms in place for users, enabling them to share the right content with the right audience. With all these efforts, privacy customizations remain hard for users across the sites. Existing research that addresses this problem mainly focuses on semi-supervised strategies that introduce extra complexity by requiring the user to manually specify initial privacy preferences for their friends. In this work, we suggest a deep reinforcement learning framework that can dynamically generate privacy labels for users in OSNs. We evaluated our framework on a 1 year crawl of Twitter data, using different types of recurrent units in recurrent neural networks (RNN): Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Simple RNN. Our experiments revealed that LSTM performed better than GRU in terms of top users detection accuracy and the ranked dependence between the generated privacy labels and estimated user trust values.
|
|
| 7. |
- Jaradat, Shatha
(författare)
-
Mining of User Profiles in Online Social Networks for Improved Personalized Recommendations
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- We have focused on influencer-based marketing in online social networks as a source of implicit learning about the preferences of social media users. Those users who use social networks on a daily basis are also the online shoppers who are confronted with huge information overload and a wide variety of online products and brands to choose from. The role of digital influencers in promoting products and spreading information to a large scale of followers who engage with the influencers’ posts and interact with them is our key to better understanding of these followers’ tastes and future purchase intentions. Hence, the analysis and the extraction of fine-grained details (which we refer to as user profiling) from digital influencers media content serves in collecting more information about the implicit preferences of their followers. With this knowledge, the chances of offering social media users better personalized services are enhanced. In this thesis, we empower cross-domain recommendations through the development of novel methods and algorithms for improving personalization through the effective mining of user profiles in online social networks. We developed a semantic information extraction framework from social media textual content that is able to capture fine-grained attributes with respect to the defined online shops taxonomy. Results form the aforementioned framework have been applied as input to the approaches we proposed to incorporate extracted textual hints in supporting the visual fine-grained classification of social media images in a dynamic way. Our methods have improved the classification accuracy when compared to state-of-the-art approaches. Moreover, we suggested solutions for incorporating the extracted products’ meta-data in embedding-based personalized recommendation architectures where our strategies improved the recommendations’ quality. In order to speed up the process of preparing large scale social media images datasets for deep learning image analysis, we developed a complete framework for detailed annotation, object localization and semantic segmentation. As our focus is also directed towards the analysis of interactions between social media users, we proposed a neural reinforcement learning approach that is based on estimating the established trust levels between social media users for controlling the amount of recommended updates they get from each other. Moreover, we proposed enhanced topic modelling algorithm for supporting interpretable yet dynamic summarizations of large social media contents.
|
|
| 8. |
- Jaradat, Shatha, et al.
(författare)
-
OLLDA : A Supervised and Dynamic Topic Mining Framework in Twitter
- 2015
-
Ingår i: 2015 IEEE International Conference on Data Mining Workshop (ICDMW). - 9781467384933 ; , s. 1354-1359
-
Konferensbidrag (refereegranskat)abstract
- Analyzing media in real-time is of great importance with social media platforms at the epicenter of crunching, digesting and disseminating content to individuals connected to these platforms. Within this context, topic models, specially LDA, have gained strong momentum due to their scalability, inference power and their compact semantics. Although, state of the art topic models come short in handling streaming large chunks of data arriving dynamically onto the platform, thus hindering their quality of interpretation as well as their adaptability to information overload. As a result, in this manuscript we propose for a labelled and online extension to LDA (OLLDA), which incorporates supervision through external labeling and capability of quickly digesting real-time updates thus making it more adaptive to Twitter and platforms alike. Our proposed extension has capability of handling large quantities of newly arrived documents in a stream, and at the same time, is capable of achieving high topic inference quality given the short and often sloppy text of tweets. Our approach mainly uses an approximate inference technique based on variational inference coupled with a labeled LDA model. We conclude by presenting experiments using a one year crawl of Twitter data that shows significantly improved topical inference as well as temporal user profile classification when compared to state of the art baselines.
|
|
| 9. |
- Jaradat, Shatha, et al.
(författare)
-
Outfit2Vec : Incorporating Clothing Hierarchical MetaData into Outfits’ Recommendation
- 2020
-
Ingår i: Fashion Recommender Systems. - : Springer International Publishing. ; , s. 87-107
-
Bokkapitel (refereegranskat)abstract
- Fashion Personalisation is emerging as a major service that online retailers and brands are competing to provide. They aim to deliver more tailored recommendations to increase revenues and satisfy customers by providing them options of similar items according to their purchase history. However, many online retailers still struggle with turning customers’ data into actionable and intelligent recommendations that reflect their personalised and preferred taste of style. On the other hand due to the ever increasing use of social media, fashion brands invest in influencers’ marketing to advertise their brands to reach a larger segment of customers who strongly trust their influencers’ choices. In this context the textual and visual analysis of social media can be used to extract semantic knowledge about customers’ preferences that can be further applied in generating tailored online shopping recommendations. As style lies in the details of outfits, recommendation models should leverage the fashion metadata ranging from clothing categories and subcategories to attributes such as materials and patterns to overall style description in order to generate fine-grained recommendations. Recently, several recommendation algorithms suggested to model the latent representations of items and users with neural word embeddings approaches which showed improved results. Inspired by Paragraph Vector neural embeddings model, we present Outfit2vec and PartialOutfit2vec in which we leverage the complex relationship between user’s fashion metadata while generating outfits’ embeddings. In this paper, we also describe a methodology to generate representative vectors of hierarchically-composed fashion outfits. We evaluate our models using different strategies in comparison to the paragraph embedding models on an extensively-annotated Instagram dataset on recommendation and multi-class style classification tasks. Our models achieve better results specially in whole outfits’ ranking evaluations with an average of 22% increase.
|
|
| 10. |
|
|
