Skip to content

Commit 0e61e82

Browse files
committed
update site
1 parent 4072aa6 commit 0e61e82

23 files changed

+127
-25
lines changed

content/en/blog/ai-meetup.md

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,10 @@ title: "Upcoming Tech Talk at AICamp meetup"
33
categories: ["data"]
44
image: "/images/aimeetup-londonb.png"
55
date: 2024-03-22
6+
7+
aliases:
8+
- "/upcoming-tech-talk-at-aicamp-meetup/"
9+
url: "/psychology-ai-tool/aicamp-meetup/"
610
---
711

812
## Upcoming Tech Talk: at the AICamp AI Meetup (London): AI, Generative AI, LLMs
@@ -11,7 +15,7 @@ date: 2024-03-22
1115

1216
{{< youtube MpZLl9gTEIw >}}
1317

14-
We're pleased to announce that **Harmony** will be showcased at the upcoming **AICamp AI Meetup in London** on **27 March**.
18+
We're pleased to announce that the [AI tool](/psychology-ai-tool/) **Harmony** will be showcased at the upcoming **AICamp AI Meetup in London** on **27 March**.
1519

1620
You are invited to AICamp's monthly in-person AI meetup in London. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers
1721

content/en/blog/aidl-meetup.md

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,11 @@ categories:
44
- "ai-in-research"
55
image: "/images/aidl.jpg"
66
date: 2024-09-20
7-
url: "/psychology/aidl-meetup"
7+
8+
9+
aliases:
10+
- "/psychology/aidl-meetup/"
11+
url: "/psychology-ai-tool/aidl-meetup/"
812
---
913

1014
## Tech Talk at the AI|DL AI Meetup (London) Artificial Intelligence and Deep Learning for Enterprise
@@ -15,7 +19,7 @@ Topic: **Harmony: a free online tool using LLMs for research in psychology and s
1519

1620
Speaker: [Thomas Wood](https://freelancedatascientist.net/) ([Fast Data Science](https://fastdatascience.com/))
1721

18-
Description: Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a free online tool that uses generative AI and LLMs to help researchers compare items in questionnaires such as [GAD-7](/compare-harmonise-instruments/gad-7-vs-sdq/) (used to measure anxiety), even when they are written in different languages. Harmony is open source under [MIT License](https://github.com/harmonydata/harmony/blob/main/LICENSE) and is written in Python, and uses [HuggingFace Sentence Transformers](/measuring-the-performance-of-nlp-algorithms/) to find similarities between questionnaires.
22+
Description: Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a [free online tool](/psychology-ai-tool/) that uses generative AI and LLMs to help researchers compare items in questionnaires such as [GAD-7](/compare-harmonise-instruments/gad-7-vs-sdq/) (used to measure anxiety), even when they are written in different languages. Harmony is open source under [MIT License](https://github.com/harmonydata/harmony/blob/main/LICENSE) and is written in Python, and uses [HuggingFace Sentence Transformers](/measuring-the-performance-of-nlp-algorithms/) to find similarities between questionnaires.
1923

2024
[Harmony Discovery](/discovery/) will soon allow researchers to discover datasets using a vector search.
2125

content/en/blog/back-to-the-future-retrospectively-harmonizing-questionnaire-data.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ Now more than ever, the international research community are keen to determine w
1919

2020
As an alternative to direct replication, researchers may choose to reach out to others in the field who either have access to, or are in the process of collecting, comparable data. Indeed many researchers, particularly those in the life and social sciences, routinely make use of large, ongoing studies that collect a variety of data for multiple purposes (e.g. [longitudinal](/item-harmonisation/harmony-a-free-ai-tool-to-merge-longitudinal-studies) population studies). In practice however, much of our research is designed and carried out in silos – with different research groups tackling similar research questions using widely different designs and measures. Even if a researcher is successful in identifying data that are similar to their original work, minor differences in the design or measures may limit the comparability. What are researchers to do in such situations?
2121

22-
One increasingly popular option is retrospective [harmonisation](data-harmonisation). This involves taking existing data from two or more disparate sources, and transforming the data in some way in order to make it directly comparable across sources. Let’s look at a simple, hypothetical example. Say a researcher wants to examine the relationship between level of [education](/data-harmonisation-in-education) and [depression](/harmonisation-validation/promis-depression-subscale), and whether this varies across two datasets, each from a different country. In dataset A, participants were asked to report their highest qualification out of a list of 10 options ranging from “no formal education” to “doctoral education”, whereas in dataset B there was a simple question that asked participants whether they completed a Bachelor’s degree (yes/no). The 10-option question in dataset A could be recoded to match the variable in dataset B, by collapsing all of the categories above and below Bachelor’s level. In many cases, retrospective harmonisation can be applied on an ad-hoc basis, using simple, logical recoding strategies such as this.
22+
One increasingly popular option is retrospective [harmonisation](/data-harmonisation). This involves taking existing data from two or more disparate sources, and transforming the data in some way in order to make it directly comparable across sources. Let’s look at a simple, hypothetical example. Say a researcher wants to examine the relationship between level of [education](/data-harmonisation-in-education) and [depression](/harmonisation-validation/promis-depression-subscale), and whether this varies across two datasets, each from a different country. In dataset A, participants were asked to report their highest qualification out of a list of 10 options ranging from “no formal education” to “doctoral education”, whereas in dataset B there was a simple question that asked participants whether they completed a Bachelor’s degree (yes/no). The 10-option question in dataset A could be recoded to match the variable in dataset B, by collapsing all of the categories above and below Bachelor’s level. In many cases, retrospective harmonisation can be applied on an ad-hoc basis, using simple, logical recoding strategies such as this.
2323

2424
However, not all constructs can be measured with such simple, categorical questions. Take the above outcome variable (depression) for instance. Depression is a complex, heterogeneous experience, characterized by a multitude of symptoms that can be experienced to various degrees and in different combinations. In large-scale surveys, depression is typically measured with standardized questionnaires – participants are asked to report on a range of symptoms, their responses are assigned numerical values, and these are summed to form a “total depression score” for each individual. Although this remains the most viable and plausible strategy for measuring something as complex as depression, there is no “gold standard” questionnaire that is universally adopted by researchers. Instead, there are well over 200 established depression scales. In a [recent review](https://www.closer.ac.uk/wp-content/uploads/210715-Harmonisation-measurement-properties-mental-health-measures-british-cohorts.pdf) (McElroy et al., 2020), we noted that the content of these questionnaires can differ markedly, e.g. different symptoms are assessed, or different response options are used.
2525

content/en/blog/bmc-paper.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,8 +6,10 @@ categories:
66
- "psychology"
77

88
image: "/images/bmc.png"
9-
url: "/bmc-psychiatry-paper"
109

10+
aliases:
11+
- "/bmc-psychiatry-paper/"
12+
url: "/ai-in-mental-health/bmc-psychiatry-paper/"
1113
---
1214

1315
# BMC Psychiatry has published our paper validating Harmony on real-world data

content/en/blog/data-harmonisation-education.md

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,11 @@ title: "Data Harmonisation in Education"
33
categories: ["data"]
44
image: "/images/17- Data harmonisation in education.svg"
55
date: 2024-06-05
6+
7+
8+
aliases:
9+
- "/data-harmonisation-in-education/"
10+
url: "/data-harmonisation/data-harmonisation-in-education/"
611
---
712

813
# Data Harmonisation in Education: Overview
@@ -11,7 +16,7 @@ The term ‘harmonisation’ has often been used in different contexts – for e
1116

1217
Now, the underlying degree of interaction between all the players involved can run a lot deeper and tighter when we transition from collaboration, partnership, and cooperation to integration, community, harmonisation, and interdependence. We might also infer that integration of any kind is an entire process where multiple steps are involved based on the level of commitment coming from the various actors or parties involved.
1318

14-
Data harmonisation has been used for well over a decade in policy documents. For example, the term “harmonisation” was coined in EHEA (European Higher Education Area) as a chief element in the Sorbonne Declaration of June 1999, signed as architecture of reform of the EU’s higher education system.
19+
[Data harmonisation](/data-harmonisation/) has been used for well over a decade in policy documents. For example, the term “harmonisation” was coined in the EHEA (European Higher Education Area) as a chief element in the Sorbonne Declaration of June 1999, signed as architecture of reform of the EU’s higher education system.
1520

1621
The African union has developed a similar framework to harmonise their higher education system where their policy documentation clearly refers to the entire process as “harmonisation”.
1722

content/en/blog/data-harmonisation.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -114,7 +114,7 @@ Let's explore this need further in various sectors:
114114

115115
7. **Supply Chain Management**: In global supply chains, harmonising data related to inventory levels, supplier performance, and logistics is crucial for efficiency. Differing data standards across countries and companies can lead to inefficiencies and disruptions.
116116

117-
8. **Education and Comparative Studies**: For educational research and international comparisons of educational systems, data harmonisation helps in understanding the effectiveness of different educational approaches and in making cross-country comparisons.
117+
8. **Education and Comparative Studies**: For educational research and international comparisons of educational systems, data harmonisation [helps in understanding the effectiveness of different educational approaches and in making cross-country comparisons](/data-harmonisation/data-harmonisation-in-education/).
118118

119119
9. **Telecommunications**: Telecom companies use data harmonisation to integrate customer data, usage patterns, and network data from various sources. This helps in improving network efficiency, customer service, and in developing new services.
120120

@@ -136,7 +136,7 @@ Tools like Harmony, designed specifically for the [retrospective harmonisation o
136136
Companies like EPAM and TIBCO highlight the strategic importance of data harmonisation. They emphasize how it can provide a competitive edge by ensuring data consistency across an organization, improving decision-making, and streamlining operations.
137137

138138
**Future and Role in AI and Machine Learning**
139-
The future of data harmonisation is closely intertwined with advancements in AI and machine learning. These technologies have the potential to automate the harmonisation process, making it more efficient and accurate. AI can assist in identifying patterns, inconsistencies, and correlations in large datasets, while machine learning algorithms can learn from data to improve the harmonisation process over time, adapting to changes in data structures and formats.
139+
The future of data harmonisation is closely intertwined with advancements in AI and machine learning. These technologies have the potential to automate the harmonisation process, making it more efficient and accurate. AI can assist in identifying patterns, [inconsistencies](/data-harmonisation/harmonising-questionnaire-data-consistency/), and correlations in large datasets, while machine learning algorithms can learn from data to improve the harmonisation process over time, adapting to changes in data structures and formats.
140140

141141
In summary, data harmonisation is a critical and practical process in various industries, enhancing data quality, decision-making, and operational efficiency. The evolution of this field, particularly with the integration of AI and machine learning, holds significant promise for even more streamlined and effective data management in the future.
142142

content/en/blog/harmony-going-forward-5-things-implementation-science-has-taught-us-to-focus-on.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,8 @@ image: /images/blog/noah-buscher-x8ZStukS2PM-unsplash-1536x880.jpg
77
aliases:
88
- /blog/harmony-going-forward/
99
- /harmony-going-forward-5-things-implementation-science-has-taught-us-to-focus-on
10+
- /harmony-going-forward/
11+
url: "/ai-in-mental-health/harmony-going-forward/"
1012
---
1113

1214
**5 key things Implementation Science has taught us** **to focus on**

content/en/blog/harmony-methodscon.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,11 @@ title: "Harmony at MethodsCon: Futures in Manchester"
33
categories: ["psychology"]
44
image: "/images/pexels-szymon-shields-1503561-7847361.jpg"
55
date: 2024-09-06
6+
7+
8+
aliases:
9+
- "/harmony-at-methodscon-futures-in-manchester/"
10+
url: "/ai-in-mental-health/harmony-at-methodscon-futures/"
611
---
712

813
## MethodsCon in Manchester

content/en/blog/harmony-multilingual.md

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,8 +4,12 @@ description: How we are handling multiple languages in the Harmony project
44
date: 2023-08-19
55
categories: ["nlp"]
66
image: /images/multilingual.png
7+
8+
79
aliases:
8-
- /harmony-supports-8-languages
10+
- "/harmony-supports-8-languages/"
11+
- "/harmony-supports-over-8-languages/"
12+
url: "/psychology-ai-tool/harmony-many-languages/"
913
---
1014

1115
> Привет Гармония! 哈莫尼可以让中英文和谐! שלום הרמוני Harmony peut aussi harmoniser les instruments en français.
@@ -38,7 +42,7 @@ Harmony is easy to use and accessible online. You can upload your own questionna
3842

3943
By supporting [multiple languages](https://fastdatascience.com/multilingual-natural-language-processing/), Harmony can also help you reach a wider audience and collaborate with researchers from different countries and cultures. Harmony is constantly being updated and improved to provide you with the best service possible.
4044

41-
If you are interested in using Harmony or learning more about it, please visit [the Harmony website](https://harmonydata.ac.uk) or [contact us](/contact). We would love to hear from you and get your feedback on our tool.
45+
If you are interested in using Harmony or learning more about it, please visit [the Harmony website](https://harmonydata.ac.uk) or [contact us](/contact). We would love to hear from you and [get your feedback](/psychology-ai-tool/what-features-would-you-like-to-see-in-harmony/) on our [tool](/psychology-ai-tool/).
4246

4347
{{< image src="images/reiwa.svg" alt="Reiwa in Japanese" title="Reiwa in Japanese" >}}
4448

content/en/blog/kaggle.md

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,14 +3,17 @@ title: "Harmony on Kaggle"
33
date: 2024-02-01
44
categories: ["development"]
55
image: "/images/kaggle.jpg"
6-
aliases: "/kaggle"
6+
7+
aliases:
8+
- "/kaggle/"
9+
url: "/psychology-ai-tool/kaggle/"
710
---
811

912
## Harmony launches on Kaggle!
1013

1114
We are proud to have launched our first competition on Kaggle!
1215

13-
The primary challenge of this competition is to develop a tool or method that can accurately extract questionnaire questions from documents, primarily PDFs.
16+
The primary challenge of this competition is to develop an [AI tool](/psychology-ai-tool/) or method that can accurately extract questionnaire questions from documents, primarily PDFs.
1417

1518
This competition offers a unique opportunity for participants to contribute to the field of natural language processing and document analysis while developing solutions that have real-world applications. We encourage participants to think creatively, leverage available resources, and push the boundaries of current technologies.
1619

0 commit comments

Comments
 (0)