With the bloom of machine learning, a massive amount of data has been used in the training process of machine learning. A tremendous amount of this data is user-generated data which allows the machine learning models to produce accurate results and personalized services. Nevertheless, I recognize the importance of preserving the privacy of individuals by protecting their information in the training process. One privacy attack that affects individuals is the private attribute inference attack. The private attribute attack is the process of inferring individuals' information that they do not explicitly reveal, such as age, gender, location, and occupation. The impacts of this go beyond knowing the information as individuals face potential risks. Furthermore, some applications need sensitive data to train the models and predict helpful insights and figuring out how to build privacy-preserving machine learning models will increase the capabilities of these applications.However, improving privacy affects the data utility which leads to a dilemma between privacy and utility. The utility of the data is measured by the quality of the data for different tasks. This trade-off between privacy and utility needs to be maintained to satisfy the privacy requirement and the result quality. To achieve more scalable privacy-preserving machine learning models, I investigate the privacy risks that affect individuals' private information in distributed machine learning. Even though the distributed machine learning has been driven by privacy concerns, privacy issues have been proposed in the literature which threaten individuals' privacy. In this dissertation, I investigate how to measure and protect individuals' privacy in centralized and distributed machine learning models. First, a privacy-preserving text representation learning is proposed to protect users' privacy that can be revealed from user generated data. Second, a novel privacy-preserving text classification for split learning is presented to improve users' privacy and retain high utility by defending against private attribute inference attacks.

Social media has become an important means of user-centered information sharing and communications in a gamut of domains, including news consumption, entertainment, marketing, public relations, and many more. The low cost, easy access, and rapid dissemination of information on social media draws a large audience but also exacerbate the wide propagation of disinformation including fake news, i.e., news with intentionally false information. Disinformation on social media is growing fast in volume and can have detrimental societal effects. Despite the importance of this problem, our understanding of disinformation in social media is still limited. Recent advancements of computational approaches on detecting disinformation and fake news have shown some early promising results. Novel challenges are still abundant due to its complexity, diversity, dynamics, multi-modality, and costs of fact-checking or annotation.

Social media data opens the door to interdisciplinary research and allows one to collectively study large-scale human behaviors otherwise impossible. For example, user engagements over information such as news articles, including posting about, commenting on, or recommending the news on social media, contain abundant rich information. Since social media data is big, incomplete, noisy, unstructured, with abundant social relations, solely relying on user engagements can be sensitive to noisy user feedback. To alleviate the problem of limited labeled data, it is important to combine contents and this new (but weak) type of information as supervision signals, i.e., weak social supervision, to advance fake news detection.

The goal of this dissertation is to understand disinformation by proposing and exploiting weak social supervision for learning with little labeled data and effectively detect disinformation via innovative research and novel computational methods. In particular, I investigate learning with weak social supervision for understanding disinformation with the following computational tasks: bringing the heterogeneous social context as auxiliary information for effective fake news detection; discovering explanations of fake news from social media for explainable fake news detection; modeling multi-source of weak social supervision for early fake news detection; and transferring knowledge across domains with adversarial machine learning for cross-domain fake news detection. The findings of the dissertation significantly expand the boundaries of disinformation research and establish a novel paradigm of learning with weak social supervision that has important implications in broad applications in social media.