Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks
97
0
0.0
(
0
)
Added by
Karan Sikka
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
There has been an explosion of multimodal content generated on social media networks in the last few years, which has necessitated a deeper understanding of social media content and user behavior. We present a novel content-independent content-user-reaction model for social multimedia content analysis. Compared to prior works that generally tackle semantic content understanding and user behavior modeling in isolation, we propose a generalized solution to these problems within a unified framework. We embed users, images and text drawn from open social media in a common multimodal geometric space, using a novel loss function designed to cope with distant and disparate modalities, and thereby enable seamless three-way retrieval. Our model not only outperforms unimodal embedding based methods on cross-modal retrieval tasks but also shows improvements stemming from jointly solving the two tasks on Twitter data. We also show that the user embeddings learned within our joint multimodal embedding model are better at predicting user interests compared to those learned with unimodal content on Instagram data. Our framework thus goes beyond the prior practice of using explicit leader-follower link information to establish affiliations by extracting implicit content-centric affiliations from isolated users. We provide qualitative results to show that the user clusters emerging from learned embeddings have consistent semantics and the ability of our model to discover fine-grained semantics from noisy and unstructured data. Our work reveals that social multimodal content is inherently multimodal and possesses a consistent structure because in social networks meaning is created through interactions between users and content.
rate research
Read More
This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are not comparable. In this work, we introduce an end-to-end deep multimodal convolutional-recurrent network for learning both vision and language representations simultaneously to infer image-text similarity. The model learns which pairs are a match (positive) and which ones are a mismatch (negative) using a hinge-based triplet ranking. To learn about the joint representations, we leverage our newly extracted collection of tweets from Twitter. The main characteristic of our dataset is that the images and tweets are not standardized the same as the benchmarks. Furthermore, there can be a higher semantic correlation between the pictures and tweets contrary to benchmarks in which the descriptions are well-organized. Experimental results on MS-COCO benchmark dataset show that our model outperforms certain methods presented previously and has competitive performance compared to the state-of-the-art. The code and dataset have been made available publicly.
User representations are routinely used in recommendation systems by platform developers, targeted advertisements by marketers, and by public policy researchers to gauge public opinion across demographic groups. Computer scientists consider the problem of inferring user representations more abstractly; how does one extract a stable user representation - effective for many downstream tasks - from a medium as noisy and complicated as social media? The quality of a user representation is ultimately task-dependent (e.g. does it improve classifier performance, make more accurate recommendations in a recommendation system) but there are proxies that are less sensitive to the specific task. Is the representation predictive of latent properties such as a persons demographic features, socioeconomic class, or mental health state? Is it predictive of the users future behavior? In this thesis, we begin by showing how user representations can be learned from multiple types of user behavior on social media. We apply several extensions of generalized canonical correlation analysis to learn these representations and evaluate them at three tasks: predicting future hashtag mentions, friending behavior, and demographic features. We then show how user features can be employed as distant supervision to improve topic model fit. Finally, we show how user features can be integrated into and improve existing classifiers in the multitask learning framework. We treat user representations - ground truth gender and mental health features - as auxiliary tasks to improve mental health state prediction. We also use distributed user representations learned in the first chapter to improve tweet-level stance classifiers, showing that distant user information can inform classification tasks at the granularity of a single message.
In this paper we present a novel interactive multimodal learning system, which facilitates search and exploration in large networks of social multimedia users. It allows the analyst to identify and select users of interest, and to find similar users in an interactive learning setting. Our approach is based on novel multimodal representations of users, words and concepts, which we simultaneously learn by deploying a general-purpose neural embedding model. We show these representations to be useful not only for categorizing users, but also for automatically generating user and community profiles. Inspired by traditional summarization approaches, we create the profiles by selecting diverse and representative content from all available modalities, i.e. the text, image and user modality. The usefulness of the approach is evaluated using artificial actors, which simulate user behavior in a relevance feedback scenario. Multiple experiments were conducted in order to evaluate the quality of our multimodal representations, to compare different embedding strategies, and to determine the importance of different modalities. We demonstrate the capabilities of the proposed approach on two different multimedia collections originating from the violent online extremism forum Stormfront and the microblogging platform Twitter, which are particularly interesting due to the high semantic level of the discussions they feature.
With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.
Multimodal Sentiment Analysis in Real-life Media (MuSe) 2020 is a Challenge-based Workshop focusing on the tasks of sentiment recognition, as well as emotion-target engagement and trustworthiness detection by means of more comprehensively integrating the audio-visual and language modalities. The purpose of MuSe 2020 is to bring together communities from different disciplines; mainly, the audio-visual emotion recognition community (signal-based), and the sentiment analysis community (symbol-based). We present three distinct sub-challenges: MuSe-Wild, which focuses on continuous emotion (arousal and valence) prediction; MuSe-Topic, in which participants recognise domain-specific topics as the target of 3-class (low, medium, high) emotions; and MuSe-Trust, in which the novel aspect of trustworthiness is to be predicted. In this paper, we provide detailed information on MuSe-CaR, the first of its kind in-the-wild database, which is utilised for the challenge, as well as the state-of-the-art features and modelling approaches applied. For each sub-challenge, a competitive baseline for participants is set; namely, on test we report for MuSe-Wild a combined (valence and arousal) CCC of .2568, for MuSe-Topic a score (computed as 0.34$cdot$ UAR + 0.66$cdot$F1) of 76.78 % on the 10-class topic and 40.64 % on the 3-class emotion prediction, and for MuSe-Trust a CCC of .4359.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
