Topic detection and tracking on heterogeneous information

Abstract

Given the proliferation of social media and the abundance of news feeds, a substantial amount of real-time content is distributed through disparate sources, which makes it increasingly difficult to glean and distill useful information. Although combining heterogeneous sources for topic detection has gained attention from several research communities, most of them fail to consider the interaction among different sources and their intertwined temporal dynamics. To address this concern, we studied the dynamics of topics from heterogeneous sources by exploiting both their individual properties (including temporal features) and their inter-relationships. We first implemented a heterogeneous topic model that enables topic-topic correspondence between the sources by iteratively updating its topic-word distribution. To capture temporal dynamics, the topics are then correlated with a time-dependent function that can characterise its social response and popularity over time. We extensively evaluate the proposed approach and compare to the state-of-the-art techniques on heterogeneous collection. Experimental results demonstrate that our approach can significantly outperform the existing ones.

Smart transit car design based on STM32 and OPENMV

“…According to the difference of the reflectivity of the red and white colors to the light, the infrared radiation is continuously transmitted to the ground through the infrared transmitter, and the light intensity received by the photosensitive receiver is used for tracking. When the receiving end receives a weak signal, it can be determined that it has hit the red line [3]. When the light is not received or the signal is very weak, the photosensitive triode is closed, making the detection circuit output a highlevel signal.…”

Adapting the influences of publishers to perform news event detection

“…In recent years, LDA has been adopted and improved by many applications to solve different problems. The LDA concept has been utilised to apply news and tweets from heterogeneous sources to topic detection and tracking [46] or through the evolution of news topics over time to realise the tracking and evolution of topics in news text [24]. Figure 6 illustrates the LDA model, where C z represents each clustered news set and h k represents the news headline in news set C z .…”

Multi‐level feature optimization and multimodal contextual fusion for sentiment analysis and emotion classification

“…The multimodal data from the internet is analyzed for understanding the user's sentiment or emotion towards a product or a service . The sentiment analysis and affective computing have a lot of challenges such as subjectivity analysis, aspect detection and consideration, topic detection and tracking, document summarization . The earlier research concentrates on textual data for sentiment analysis but more recently multimodal data such as textual‐acoustic‐visual modality were considered for sentiment classification and affective computing .…”