Related Experiment Video
Updated: Jan 21, 2026
04:04
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
942
Comparison of text processing methods in social media-based signal detection
Natalie Gavrielov-Yusim1, Marie-Laure Kürzinger2, Chihiro Nishikawa2
1R&D, Data2Life, Tel Aviv, Israel.
Pharmacoepidemiology and Drug Safety
|August 9, 2019
Summary
Natural language processing (NLP) and machine learning (ML) methods effectively identify adverse events (AEs) in social media. NLP shows higher consistency with reference data than basic co-occurrence methods for AE detection.
Area of Science:
- Pharmacovigilance and computational linguistics.
- Application of machine learning and natural language processing in healthcare.
Background:
- Adverse event (AE) identification from social media (SM) is crucial for pharmacovigilance.
- Existing methods include co-occurrence-based machine learning (ML) and more complex natural language processing (NLP) techniques.
Purpose of the Study:
- To compare the efficacy of co-occurrence and NLP methods in identifying AEs and signals of disproportionate reporting (SDR) from patient-generated SM.
- To evaluate the performance of lift in SM-based signal detection (SD).
Main Methods:
- Analysis of a corpus of SM posts from online patient forums.
- Comparison with spontaneously reported VigiBase data as a reference.
- Assessment of AE and SDR identification consistency and timeliness.
Main Results:
- NLP-identified AEs showed 93% consistency with VigiBase AEs, compared to 57% for co-occurrence methods.
- Co-occurrence methods identified SDRs earlier in up to 55.3% of cases, while NLP identified them earlier in up to 32.1%.
- Lift-based SM signal detection performed comparably to frequentist methods.
Conclusions:
- Social media is a valuable complementary data source for pharmacovigilance.
- The choice of SM processing level depends on desired balance between false positives and negatives.
- Further consideration of SM data integration into routine pharmacovigilance is recommended.
Keywords:
adverse event (AE)liftmachine learning (ML)natural language processing (NLP)pharmacoepidemiologysignal of disproportionate reporting (SDR)social media (SM)More Related Videos
Related Concept Videos
02:57The Sense of Self: Reflected Self-Appraisal and Social Comparison
55.5K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
55.5K
01:27Sources of Self-Esteem III: Social Comparison
247
Social comparison plays a fundamental role in the evaluation of personal success and self-worth. Rather than assessing our achievements in isolation, we interpret their significance relative to personal goals and critically in comparison to the performance of others. A grade of B in a mathematics exam might elicit pride if one's expectation was a C, yet result in disappointment if an A was anticipated or if peers achieved superior results. These comparative evaluations illustrate how both...
247
01:15Causes of Social Behavior II: Cognitive Processes
196
Cognitive processes affect social behavior by guiding how individuals perceive, interpret, and respond to social stimuli. These mental processes enable individuals to assess others' behaviors, attribute causes to their actions, and form expectations based on past experiences.Causes of Behavior and Social JudgmentsIndividuals determine the causes of others' behaviors by distinguishing between personal traits and external circumstances. For example, if a friend frequently arrives late, an...
196
00:52Social Proof
31.5K
Social proof is a form of persuasion based on comparison and conformity. People compare their behavior and actions to what others are doing and will change to conform to do what their peers do.
31.5K
02:06Social Exchange Theory
39.5K
We have discussed why we form relationships, what attracts us to others, and different types of love. But what determines whether we are satisfied with and stay in a relationship? One theory that provides an explanation is social exchange theory. According to social exchange theory, we act as naïve economists in keeping a tally of the ratio of costs and benefits of forming and maintaining a relationship with others (Rusbult & Van Lange, 2003).
39.5K
01:28Automatic Processing and Automatic Social Behavior
223
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
223