Health outcomes in modern society are often shaped by peer interactions. Increasingly, a significant fraction of such interactions happen online and can have an impact on various mental health and behavioral health outcomes. Guided by appropriate social and psychological research, we conduct an observational study to understand the interactions between clinically depressed users and their ego-network when contrasted with a differential control group of normal users and their ego-network. Specifically, we examine if one can identify relevant linguistic and emotional signals from social media exchanges to detect symptomatic cues of depression. We observe significant deviations in the behavior of depressed users from the control group. Reduced and nocturnal online activity patterns, reduced active and passive network participation, increase in negative sentiment or emotion, distinct linguistic styles (e.g. self-focused pronoun usage), highly clustered and tightly-knit neighborhood structure, and little to no exchange of influence between depressed users and their ego-network over time are some of the observed characteristics. Based on our observations, we then describe an approach to extract relevant features and show that building a classifier to predict depression based on such features can achieve an F-score of 90%.

Some rights reserved. For more information, please see the item record link above.

The rapid advances in e-commerce and Web 2.0 technologies have greatly increased the impact of commercial advertisements on the general public. As a key enabling technology, a multitude of recommender systems exists which analyzes user features and browsing patterns to recommend appealing advertisements to users. In this work, we seek to study the characteristics or attributes that characterize an effective advertisement and recommend a useful set of features to aid the designing and production processes of commercial advertisements. We analyze the temporal patterns from multimedia content of advertisement videos including auditory, visual and textual components, and study their individual roles and synergies in the success of an advertisement. The objective of this work is then to measure the effectiveness of an advertisement, and to recommend a useful set of features to advertisement designers to make it more successful and approachable to users. Our proposed framework employs the signal processing technique of cross modality feature learning where data streams from different components are employed to train separate neural network models and are then fused together to learn a shared representation. Subsequently, a neural network model trained on this joint feature embedding representation is utilized as a classifier to predict advertisement effectiveness. We validate our approach using subjective ratings from a dedicated user study, the sentiment strength of online viewer comments, and a viewer opinion metric of the ratio of the Likes and Views received by each advertisement from an online platform.

No abstract

Detecting and identifying user intent from text, both written and spoken, plays an important role in modelling and understand dialogs. Existing research for intent discovery model it as a classification task with a predefined set of known categories. To generailze beyond these preexisting classes, we define a new task of open intent discovery. We investigate how intent can be generalized to those not seen during training. To this end, we propose a two-stage approach to this task -predicting whether an utterance contains an intent, and then tagging the intent in the input utterance. Our model consists of a bidirectional LSTM with a CRF on top to capture contextual semantics, subject to some constraints. Self-attention is used to learn long distance dependencies. Further, we adapt an adversarial training approach to improve robustness and perforamce across domains. We also present a dataset of 25k real-life utterances that have been labelled via crowd sourcing. Our experiments across different domains and real-world datasets show the effectiveness of our approach, with less than 100 annotated examples needed per unique domain to recognize diverse intents. The approach outperforms state-of-the-art baselines by 5-15% F1 score points.